Solid oxide electrolysis cell system optimization control method and apparatus

Abstract

The application provides a solid oxide electrolysis cell system optimization control method and device. The solid oxide electrolysis cell system optimization control method comprises the following steps: obtaining internal temperature distribution data of a SOEC (solid oxide electrolysis cell), filtering and estimating the obtained temperature distribution data to obtain a temperature gradient; performing parameter traversal on the SOEC system, analyzing the relationship between the temperature and the electrical performance under different parameter combinations, obtaining the temperature and electrical performance curves in the full parameter combination range, optimizing the temperature and electrical performance curves in the full parameter combination range, and determining the target operation parameters of the SOEC system; and using a neural network predictive control algorithm to control the temperature of the SOEC system by taking the target operation parameters as the feedforward input and the temperature gradient as the controlled variable. The purpose of improving the safety and efficiency of the system is achieved.

Description

Technical Field

[0001] This invention belongs to the field of hydrogen energy technology, and in particular relates to an optimized control method and device for a solid oxide electrolysis cell system. Background Technology

[0002] Since SOEC operates in a high-temperature environment and has very high requirements for airtightness, it cannot directly measure temperature by drilling too many holes and placing thermocouples in the holes.

[0003] Current technology cannot monitor the temperature distribution within an SOEC stack without compromising its sealing. It also cannot adjust gas flow to maintain the SOEC stack's temperature distribution within a safe range and optimize system efficiency amidst fluctuations in electrolysis power input. Excessive internal temperature gradients can cause the cells to bend, and over time, even rupture, resulting in poor system safety and low efficiency. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention provides an optimized control method and device for a solid oxide electrolysis cell system, which at least partially solves the problems of poor safety and low efficiency of the existing system.

[0005] In a first aspect, embodiments of this disclosure provide an optimized control method for a solid oxide electrolysis cell system, including:

[0006] The internal temperature distribution data of the SOEC stack is obtained, and the obtained temperature distribution data is filtered and estimated to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell.

[0007] The SOEC system is subjected to parameter traversal, and the relationship between temperature and electrical performance under different parameter combinations is analyzed to obtain temperature and electrical performance curves within the full range of parameter combinations. The temperature and electrical performance curves within the full range of parameter combinations are then optimized to determine the target operating parameters of the SOEC system.

[0008] Using the target operating parameters as feedforward inputs and the temperature gradient as the controlled variable, a neural network predictive control algorithm is used to control the temperature of the SOEC system.

[0009] Optionally, acquiring the internal temperature distribution data of the SOEC stack includes:

[0010] The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

[0011] Optionally, the filtering and estimation of the obtained temperature distribution data includes:

[0012] The obtained temperature distribution data is filtered and estimated using the extended Kalman filter algorithm.

[0013] Optionally, the optimization of the temperature and electrical performance curves across the entire parameter combination range includes:

[0014] With the goals of maximizing efficiency and minimizing the temperature difference between inlet and outlet, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves across the entire parameter combination range.

[0015] Optionally, the step of using a neural network predictive control algorithm to control the temperature of the SOEC system with the target operating parameters as feedforward input and the temperature gradient as the controlled variable includes:

[0016] The disturbance input current generated by the change in renewable energy power is used as the input parameter of the neural network predictive control algorithm.

[0017] Secondly, embodiments of this disclosure also provide an optimized control device for a solid oxide electrolysis cell system, comprising:

[0018] The SOEC stack temperature distribution observation module is used to acquire internal temperature distribution data of the SOEC stack, filter and estimate the acquired temperature distribution data to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell.

[0019] The optimal efficiency identification module is used to perform parameter traversal on the SOEC system, analyze the relationship between temperature and electrical performance under different parameter combinations, obtain temperature and electrical performance curves within the full range of parameter combinations, optimize the temperature and electrical performance curves within the full range of parameter combinations, and thus determine the target operating parameters of the SOEC system.

[0020] The temperature gradient control module is used to control the temperature of the SOEC system using a neural network predictive control algorithm, with the target operating parameters as feedforward inputs and the temperature gradient as the controlled variable.

[0021] Optionally, acquiring the internal temperature distribution data of the SOEC stack includes:

[0022] The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

[0023] Optionally, the filtering and estimation of the obtained temperature distribution data includes:

[0024] The obtained temperature distribution data is filtered and estimated using the extended Kalman filter algorithm.

[0025] Optionally, the optimization of the temperature and electrical performance curves across the entire parameter combination range includes:

[0026] With the goals of maximizing efficiency and minimizing the temperature difference between inlet and outlet, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves across the entire parameter combination range.

[0027] Optionally, the step of using a neural network predictive control algorithm to control the temperature of the SOEC system with the target operating parameters as feedforward input and the temperature gradient as the controlled variable includes:

[0028] The disturbance input current generated by the change in renewable energy power is used as the input parameter of the neural network predictive control algorithm.

[0029] This invention provides a method and apparatus for optimizing the control of a solid oxide electrolyzer (SOEC) system. The method involves accurately acquiring the temperature distribution of the SOEC stack to obtain the temperature gradient, performing parameter traversal analysis on the SOEC system to obtain the temperature and electrical performance of the SOEC system across the entire parameter combination range, thereby determining the target operating parameters. Based on the temperature gradient and the target operating parameters, the system is controlled to improve system safety and efficiency. Attached Figure Description

[0030] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0031] Figure 1 A schematic diagram of the principle of the optimized control device for the solid oxide electrolytic cell system provided in the embodiments of this disclosure. Detailed Implementation

[0032] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0033] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0034] It should be noted that various aspects of the embodiments described below are within the scope of the appended claims. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using other structures and / or functionalities besides one or more of the aspects set forth herein.

[0035] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The illustrations only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0036] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0037] For ease of understanding, such as Figure 1 As shown, this embodiment discloses an optimized control device for a solid oxide electrolysis cell system, comprising:

[0038] The SOEC stack temperature distribution observation module is used to acquire internal temperature distribution data of the SOEC stack, filter and estimate the acquired temperature distribution data to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell.

[0039] The optimal efficiency identification module is used to perform parameter traversal on the SOEC system, analyze the relationship between temperature and electrical performance under different parameter combinations, obtain temperature and electrical performance curves within the full range of parameter combinations, optimize the temperature and electrical performance curves within the full range of parameter combinations, and thus determine the target operating parameters of the SOEC system.

[0040] The temperature gradient control module is used to control the temperature of the SOEC system using a neural network predictive control algorithm, with the target operating parameters as feedforward inputs and the temperature gradient as the controlled variable.

[0041] Optionally, acquiring the internal temperature distribution data of the SOEC stack includes:

[0042] The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

[0043] The SOEC stack nonlinear model was constructed based on historical data and nonlinear models of the SOEC stack.

[0044] Optionally, the filtering and estimation of the obtained temperature distribution data includes:

[0045] The obtained temperature distribution data is filtered and estimated using the extended Kalman filter algorithm.

[0046] A nonlinear model of the SOEC fuel cell stack was built and verified, and its internal temperature distribution data were obtained under different operating conditions.

[0047] The extended Kalman filter algorithm is used to filter and estimate the obtained temperature distribution data to construct an SOEC stack temperature distribution observation module. This model can accurately observe the internal temperature distribution of the stack based on the collectable stack inlet and outlet temperatures.

[0048] The filtered temperature distribution is used as the controlled variable and provided to the temperature gradient control module.

[0049] Optionally, the optimization of the temperature and electrical performance curves across the entire parameter combination range includes:

[0050] With the goals of maximizing efficiency and minimizing the temperature difference between inlet and outlet, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves across the entire parameter combination range.

[0051] Perform parameter traversal on the SOEC system, adjust key parameters (such as gas flow rate, electrolysis power, etc.), and record temperature and electrical performance data under different parameter combinations.

[0052] The relationship between temperature and electrical performance under different parameter combinations was analyzed, and temperature and electrical performance curves were obtained for the entire range of parameter combinations.

[0053] With the goals of maximizing efficiency and minimizing the temperature difference between inlet and outlet, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves across the entire parameter combination range.

[0054] Select the optimal operating point from the Pareto optimization results to determine the optimal operating parameters of the system under different operating conditions.

[0055] The optimal operating parameters are used as feedforward inputs and are used as reference values ​​for the temperature gradient control module.

[0056] The temperature gradient provided by the SOEC stack temperature distribution observation module is used as the controlled variable.

[0057] The NNPC (Neural Network Predictive Control) algorithm is used to control the temperature, thereby achieving stable operation and temperature control of the SOEC reactor.

[0058] The device in this embodiment includes an SOEC stack temperature distribution observation module, an optimal efficiency identification module, and a temperature gradient control module. The SOEC stack temperature distribution observation module is built based on a nonlinear model of the stack and an extended Kalman filter observation algorithm. It can observe the changes in the internal temperature of the stack in real time based on the input and output airflow temperatures that can be collected. This module utilizes a nonlinear model and Kalman filter observation algorithm to observe the changes in the internal temperature of the stack in real time. The application of this observation module can provide more accurate temperature information, which is helpful for system optimization and control. It can accurately acquire the temperature distribution of the SOEC stack in real time, providing an accurate controlled variable for the temperature gradient control module. It can effectively optimize airflow regulation and improve the safety and efficiency of the system.

[0059] The optimal efficiency identification module combines parameter traversal and Pareto optimization methods to identify the system's optimal operating point with maximum efficiency. This module helps the system achieve optimal efficiency under different operating conditions, improving energy utilization efficiency. It achieves multi-objective optimization: by employing the Pareto optimization method, it can balance and optimize between the two objectives of maximizing efficiency and minimizing the inlet and outlet temperature difference. This allows it to obtain the system's optimal operating point under different operating conditions, improving the overall performance and efficiency of the system.

[0060] The temperature gradient control module employs a Neural Predictive Control (NNPC) algorithm to achieve temperature gradient control. By controlling the gas flow rate, it ensures that the SOEC system always operates within safe constraints and reaches its optimal operating point before and after dynamic power input. This module enhances the system's safety and security.

[0061] Optionally, the step of using a neural network predictive control algorithm to control the temperature of the SOEC system with the target operating parameters as feedforward input and the temperature gradient as the controlled variable includes:

[0062] The disturbance input current generated by the change in renewable energy power is used as the input parameter of the neural network predictive control algorithm.

[0063] First, a temperature distribution observation module for the SOEC stack based on the extended Kalman filter algorithm is established to provide the controlled variable for the temperature gradient control module to regulate the airflow. Second, parameter ergonomic analysis is performed on the SOEC system to obtain the temperature and electrical performance of the SOEC system across the entire parameter combination range. Then, with the objectives of maximizing efficiency and minimizing the inlet and outlet temperature difference, Pareto optimization is used for multi-objective optimization to obtain the optimal operating point of the system under different operating conditions. Finally, using the optimal operating parameters as feedforward and the temperature gradient provided by the SOEC stack temperature distribution observation module as the controlled variable, the NNPC algorithm is combined to achieve temperature control of the SOEC stack. By employing the Pareto optimization method, a trade-off and optimization can be made between the two objectives of maximizing efficiency and minimizing the inlet and outlet temperature difference. This allows for obtaining the optimal operating point of the system under different operating conditions, improving the overall performance and efficiency of the system. By using the optimal operating parameters as feedforward, combining the temperature gradient provided by the temperature distribution observation module as the controlled variable, and combining the NNPC algorithm, precise control of the SOEC stack temperature can be achieved. This improves the system's safety and controllability, ensuring safe operation of the system under different operating conditions.

[0064] This embodiment utilizes a temperature distribution observation module employing a nonlinear model and Kalman filter observation algorithm, an optimal efficiency identification module using parameter traversal and Pareto optimization, and a module for temperature gradient control using the NNPC algorithm. These innovations contribute to improving the performance, efficiency, and safety of SOEC systems.

[0065] This embodiment also discloses an optimized control method for a solid oxide electrolysis cell system, including:

[0066] The internal temperature distribution data of the SOEC stack is obtained, and the obtained temperature distribution data is filtered and estimated to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell.

[0067] The SOEC system is subjected to parameter traversal, and the relationship between temperature and electrical performance under different parameter combinations is analyzed to obtain temperature and electrical performance curves within the full range of parameter combinations. The temperature and electrical performance curves within the full range of parameter combinations are then optimized to determine the target operating parameters of the SOEC system.

[0068] Using the target operating parameters as feedforward inputs and the temperature gradient as the controlled variable, a neural network predictive control algorithm is used to control the temperature of the SOEC system.

[0069] Optionally, acquiring the internal temperature distribution data of the SOEC stack includes:

[0070] The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

[0071] Optionally, the filtering and estimation of the obtained temperature distribution data includes:

[0072] The obtained temperature distribution data is filtered and estimated using the extended Kalman filter algorithm.

[0073] Optionally, the optimization of the temperature and electrical performance curves across the entire parameter combination range includes:

[0074] With the goals of maximizing efficiency and minimizing the temperature difference between inlet and outlet, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves across the entire parameter combination range.

[0075] Optionally, the step of using a neural network predictive control algorithm to control the temperature of the SOEC system with the target operating parameters as feedforward input and the temperature gradient as the controlled variable includes:

[0076] The disturbance input current generated by the change in renewable energy power is used as the input parameter of the neural network predictive control algorithm.

[0077] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0078] In this disclosure, relational terms such as "first" and "second" are used merely 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. Words such as "including," "comprising," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context explicitly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0079] Additionally, as used herein, the “or” used in a list of items beginning with “at least one” indicates a separate list, such that a list of, for example, “at least one of A, B, or C” means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word “exemplary” does not imply that the described example is preferred or better than other examples.

[0080] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0081] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0082] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0083] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for optimizing the control of a solid oxide electrolysis cell system, characterized in that, include: The internal temperature distribution data of the SOEC stack is obtained, and the obtained temperature distribution data is filtered and estimated to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell. The SOEC system is subjected to parameter traversal, and the relationship between temperature and electrical performance under different parameter combinations is analyzed to obtain temperature and electrical performance curves within the full range of parameter combinations. With the goal of maximizing efficiency and minimizing the inlet and outlet temperature difference, the Pareto optimization algorithm is used to optimize the temperature and electrical performance curves within the full range of parameter combinations. The optimal operating point is selected from the Pareto optimization results to determine the optimal operating parameters of the system under different operating conditions, thereby determining the target operating parameters of the SOEC system. Using the target operating parameters as feedforward inputs, the temperature gradient as the controlled variable, and the disturbance input current generated by the change in renewable energy power as the input parameters of the neural network predictive control algorithm, the temperature of the SOEC system is controlled by the neural network predictive control algorithm.

2. The optimized control method for a solid oxide electrolytic cell system according to claim 1, characterized in that, The acquisition of internal temperature distribution data of the SOEC stack includes: The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

3. The optimized control method for a solid oxide electrolytic cell system according to claim 1, characterized in that, The filtering and estimation of the obtained temperature distribution data includes: The obtained temperature distribution data is filtered and estimated using the extended Kalman filter algorithm.

4. An optimized control device for a solid oxide electrolysis cell system, characterized in that, include: The SOEC stack temperature distribution observation module is used to acquire internal temperature distribution data of the SOEC stack, filter and estimate the acquired temperature distribution data to obtain the temperature gradient. SOEC is a solid oxide electrolytic cell. The optimal efficiency identification module is used to perform parameter traversal on the SOEC system, analyze the relationship between temperature and electrical performance under different parameter combinations, obtain temperature and electrical performance curves within the full range of parameter combinations, and optimize the temperature and electrical performance curves within the full range of parameter combinations with the goal of maximizing efficiency and minimizing the inlet and outlet temperature difference. The Pareto optimization algorithm is used to optimize the temperature and electrical performance curves within the full range of parameter combinations, select the optimal operating point from the Pareto optimization results, determine the optimal operating parameters of the system under different operating conditions, and thus determine the target operating parameters of the SOEC system. The temperature gradient control module is used to control the temperature of the SOEC system by taking the target operating parameters as feedforward inputs, the temperature gradient as the controlled variable, and the disturbance input current generated by the change in renewable energy power as input parameters of the neural network predictive control algorithm.

5. The optimized control device for a solid oxide electrolytic cell system according to claim 4, characterized in that, The acquisition of internal temperature distribution data of the SOEC stack includes: The internal temperature distribution data of the SOEC fuel cell stack was obtained based on a pre-built nonlinear model of the SOEC stack.

6. The optimized control device for a solid oxide electrolytic cell system according to claim 5, characterized in that, The filtering and estimation of the obtained temperature distribution data includes: using the extended Kalman filter algorithm to filter and estimate the obtained temperature distribution data.

Images