A power regulation method, device, equipment and storage medium of a series-parallel electric pile

Abstract

This invention discloses a power regulation method, apparatus, equipment, and storage medium for a hybrid fuel cell stack, comprising a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) connected in series. The method includes: predicting the renewable energy power generated by renewable energy generation using a trained renewable energy prediction model; when the renewable energy power is less than a first power threshold, the PEMEC undertakes the electrolysis task; when the renewable energy power is greater than or equal to the first power threshold and less than a second power threshold, the SOEC and PEMEC jointly undertake the electrolysis task; when the SOEC and PEMEC jointly undertake the electrolysis task, the operating power of the SOEC and PEMEC is dynamically adjusted according to the voltage decay rate of the SOEC and a preset decay rate threshold, so as to slow down the lifespan decay rate of the SOEC while absorbing renewable energy power. This invention can flexibly respond to renewable energy power while ensuring high electrolysis efficiency, and can completely absorb renewable energy power.

Description

Technical Field

[0001] This invention relates to the field of fuel cell stack control technology, and in particular to a power regulation method, apparatus, device, and storage medium for a hybrid fuel cell stack. Background Technology

[0002] Green electricity hydrogen production refers to the production of hydrogen using electricity generated from renewable energy sources (such as wind and solar power). With breakthroughs in clean energy technologies and the continuous improvement of the industrial chain, green electricity hydrogen production has broad development prospects.

[0003] However, fluctuating renewable energy generation requires hydrogen production equipment to adjust its power output in response to renewable energy generation. High-temperature solid oxide electrolyzers operate at high temperatures, and the repeated temperature fluctuations within the stack during power adjustments greatly complicate stack control and affect stack lifespan. Therefore, stack power adjustments are often limited, for example, to 30%-110% of the rated power. This makes it difficult to track renewable energy changes when power demand is less than 30% to ensure stack safety, potentially leading to situations where renewable energy cannot be absorbed.

[0004] Current technologies typically involve configuring a certain amount of energy storage devices in the drive system of an electrolyzer. When the output power of renewable energy generation falls below the operating range of the electrolyzer due to power fluctuations, the energy storage devices release electrical energy to bring the output power of the electrolyzer's drive system back within the operating range. However, current technologies struggle to keep pace with changes in renewable energy generation power while ensuring the electrolyzer's lifespan; furthermore, adding energy storage devices increases system costs. Summary of the Invention

[0005] The purpose of this invention is to provide a power regulation method, apparatus, equipment, and storage medium for hybrid electric stacks, in order to solve the technical problem that existing electrolyzers are unable to adjust their power according to changes in the power generation of new energy sources while ensuring their service life, thus making it impossible to absorb the power generation of new energy sources.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] Option 1: A power regulation method for a hybrid fuel cell stack, wherein a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series, and the power regulation method for the hybrid fuel cell stack includes the following steps:

[0008] Solid oxide electrolyzer (SOEC) and proton exchange membrane electrolyzer (PEMEC) are connected in series;

[0009] Predict the power output of new energy generation using a trained new energy prediction model;

[0010] When the power of the new energy source is less than the first power threshold, the electrolysis task is undertaken by the PEMEC; the first power threshold is less than the maximum adjustable power of the PEMEC.

[0011] When the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold, the electrolysis task is jointly undertaken by the SOEC and the PEMEC; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC;

[0012] When the SOEC and the PEMEC jointly undertake the electrolysis task, the operating power of the SOEC and the PEMEC is dynamically adjusted according to the voltage decay rate of the SOEC and the preset decay rate threshold, so as to slow down the life decay rate of the SOEC while absorbing the new energy power.

[0013] Optionally, dynamically adjusting the operating power of the SOEC and the PEMEC based on the voltage decay rate of the SOEC and a preset decay rate threshold includes:

[0014] When the voltage decay rate is greater than the preset decay rate threshold, the first transfer power in the working power of the SOEC is transferred to the PEMEC and continues to run for a first time.

[0015] When the voltage decay rate is less than the decay rate threshold, the second transfer power in the operating power of the PEMEC is transferred to the SOEC, and the operation continues for a second time.

[0016] The SOEC defines the lifetime extension effect of the first power transfer on the SOEC as a first lifetime factor, and the PEMEC defines the lifetime reduction effect of the second power transfer on the SOEC as a second lifetime factor, wherein the first lifetime factor is greater than the second lifetime factor.

[0017] Optionally, the step of transferring the first transfer power from the SOEC's operating power to the PEMEC includes:

[0018] During the first switching time, the first transfer power in the working power of the SOEC is transferred to the PEMEC.

[0019] Optionally, the step of transferring the second transfer power from the operating power of the PEMEC to the SOEC includes:

[0020] During the second switching time, the second transfer power from the operating power of the PEMEC is transferred to the SOEC.

[0021] Optionally, the first lifetime factor is:

[0022] After the SOEC transfers the first transfer power to the PEMEC, the operating temperature of the SOEC decreases, and the effect of the temperature reduction on the lifespan extension of the SOEC is the lifespan extension factor.

[0023] The decrease in temperature leads to a decrease in the electrolysis efficiency of the SOEC. The decrease in the electrolysis efficiency of the SOEC is converted into a lifetime reduction effect on the SOEC. The lifetime reduction effect of the decrease in electrolysis efficiency on the SOEC is called the lifetime reduction factor.

[0024] The first lifespan factor is the lifespan extension factor minus the lifespan reduction factor.

[0025] Optionally, the voltage decay rate of the SOEC can be calculated according to the following formula:

[0026] ;

[0027] in, The voltage decay rate of SOEC, This is the initial electrolysis voltage of SOEC. This is the actual electrolysis voltage of SOEC.

[0028] Optionally, before predicting the renewable energy power generation using the trained renewable energy prediction model, the method further includes:

[0029] Obtain historical data on new energy power generation within a preset time period;

[0030] The historical data of new energy power generation is used to train the new energy prediction model, resulting in a well-trained new energy prediction model.

[0031] Option 2: A power regulation device for a hybrid fuel cell stack, comprising a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) connected in series, wherein the power regulation device for the hybrid fuel cell stack includes:

[0032] The power prediction module is used to predict the power of new energy generation using a trained new energy prediction model.

[0033] The first task module is used to have the PEMEC undertake the electrolysis task when the power of the new energy source is less than a first power threshold; the first power threshold is less than the maximum adjustable power of the PEMEC.

[0034] The second task module is used to have the SOEC and PEMEC jointly undertake the electrolysis task when the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC.

[0035] The dynamic adjustment module is used to dynamically adjust the operating power of the SOEC and the PEMEC according to the voltage decay rate of the SOEC and the preset decay rate threshold when the SOEC and the PEMEC jointly undertake the electrolysis task, so as to slow down the life decay rate of the SOEC while absorbing the new energy power.

[0036] Option 3, an electronic device, comprising: a processor and a memory;

[0037] The memory stores a computer program, and the processor executes the computer program to implement the steps of Scheme 1.

[0038] Option 4: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of Option 1.

[0039] This invention provides a power regulation method, apparatus, device, and storage medium for a hybrid fuel cell stack, wherein a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series. The power regulation method for the hybrid fuel cell stack includes the following steps: predicting the renewable energy power generated by renewable energy generation using a trained renewable energy prediction model; when the renewable energy power is less than a first power threshold, the PEMEC undertakes the electrolysis task; the first power threshold is less than the maximum adjustable power of the PEMEC; when the renewable energy power is greater than or equal to the first power threshold and less than a second power threshold, the SOEC and the PEMEC jointly undertake the electrolysis task; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC; when the SOEC and the PEMEC jointly undertake the electrolysis task, dynamically adjusting the operating power of the SOEC and the PEMEC according to the voltage decay rate of the SOEC and a preset decay rate threshold, so as to slow down the lifetime decay rate of the SOEC while absorbing the renewable energy power.

[0040] Based on the above technical solution, the beneficial effects of this invention are:

[0041] This invention utilizes a hybrid approach combining two different types of electrolyzers, SOEC and PEMEC, leveraging the high electrolysis efficiency of SOEC and the rapid start-up and responsiveness of PEMEC. This allows for flexible response to renewable energy power while maintaining high electrolysis efficiency. By using a renewable energy prediction model to forecast the renewable energy power generated, temperature control can be proactively implemented based on the predicted input power to the electrolyzer, resulting in greater controllability of temperature adjustments. The specific electrolysis task plan is determined based on the relationship between the renewable energy power and preset first and second power thresholds. When SOEC and PEMEC jointly perform electrolysis, their operating power is dynamically adjusted based on the real-time degradation of SOEC. This allows for dynamic adjustment of the stack's operating power according to changes in renewable energy power, ensuring the electrolyzer's lifespan while maintaining safe and efficient operation of the SOEC stack within a safe and efficient power range. This ensures stack safety, fully utilizes renewable energy, avoids power curtailment, and improves the utilization rate of renewable energy. Attached Figure Description

[0042] Figure 1 This is a schematic flowchart illustrating an embodiment of the power regulation method for hybrid fuel cell stacks of the present invention.

[0043] Figure 2 This is a schematic diagram of the connection method of the electrolytic cell in an embodiment of the power regulation method of the hybrid fuel cell stack of the present invention;

[0044] Figure 3 This is a schematic diagram of the power regulation device of the hybrid fuel cell stack of the present invention. Detailed Implementation

[0045] This invention provides a power regulation method, apparatus, equipment, and storage medium for hybrid fuel cell stacks to solve the technical problem that existing electrolyzers cannot adjust power according to changes in new energy power generation while ensuring service life, thus making it impossible to absorb new energy power generation.

[0046] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0048] Please see Figure 1 This invention provides an embodiment of a power regulation method for a hybrid fuel cell stack, wherein a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series, and the power regulation method for the hybrid fuel cell stack includes the following steps:

[0049] S100: Predict the power output of new energy generation using a trained new energy prediction model;

[0050] S200: When the power of the new energy source is less than the first power threshold, the PEMEC shall undertake the electrolysis task; the first power threshold is less than the maximum adjustable power of the PEMEC.

[0051] S300: When the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold, the electrolysis task shall be jointly undertaken by the SOEC and the PEMEC; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC;

[0052] S400: When the SOEC and the PEMEC jointly undertake the electrolysis task, the working power of the SOEC and the PEMEC is dynamically adjusted according to the voltage decay rate of the SOEC and the preset decay rate threshold, so as to slow down the life decay rate of the SOEC while absorbing the new energy power.

[0053] The existing approach of using a single type of electrolyzer to process hydrogen from renewable energy sources (such as wind and solar power) is insufficient to keep pace with changes in renewable energy generation while ensuring the electrolyzer's lifespan. This could lead to situations where renewable energy generation cannot be processed. Therefore, this invention proposes using a mixed-use approach for different types of electrolyzers. In a preferred embodiment, a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series.

[0054] It should be noted that in the embodiments of the present invention, an SOEC and a PEMEC can be connected in series, or an electrolytic cell with an SOEC and a PEMEC connected in series can be used as a group of electrolytic cells, and multiple groups of electrolytic cells can be connected in series or in parallel.

[0055] To ensure that SOEC operates safely and efficiently while fully utilizing renewable energy and avoiding power curtailment, this invention employs a hybrid approach combining PEMEC and SOEC. This is because SOEC operates at high temperatures, improving electrolysis and hydrogen production efficiency; while PEMEC operates at low temperatures, offering faster start-up and better response. Compared to SOEC, PEMEC responds more quickly to power changes and has a wider power variability range. This hybrid approach leverages the advantages of both, flexibly responding to renewable energy while maintaining high electrolysis efficiency.

[0056] Please see Figure 2 Units 1 and 2 are connected in series. Specifically, Unit 1 can be an SOEC (Solar Energy Controlled Controller), with a rated power of 10kW and an adjustable power range of 30% to 110%, meaning the SOEC's adjustable power range is 3kW to 11kW. Unit 2 can be a PEMEC (Polymer Energy Controlled Controller), whose rated power can be set to the lower limit of the SOEC's adjustable power. For example, when the SOEC's adjustable power lower limit is 30%, the PEMEC's ​​rated power is 10kW multiplied by 30%, which equals 3kW. The PEMEC's ​​adjustable power range can be 0% to 160% of its rated power, or 0% to 4.8kW.

[0057] It should be noted that stack 1 can be PEMEC and stack 2 can be SOEC; the adjustable power range of SOEC and PEMEC can be set according to the actual situation and may vary.

[0058] In this embodiment of the invention, the source of the electrolytic cell's electrical energy can be the power generation of new energy sources, including at least photovoltaic and wind power generation (which can be simply referred to as wind and solar power generation). Considering that new energy power generation is predictable, the prediction of the electrolytic cell's electrical energy input can be achieved to a certain extent.

[0059] In step S100, the trained new energy prediction model is used to predict the new energy power of new energy generation.

[0060] In one embodiment, before predicting the renewable energy power generation using a trained renewable energy prediction model, the method further includes:

[0061] Obtain historical data on new energy power generation within a preset time period;

[0062] The historical data of new energy power generation is used to train the new energy prediction model, resulting in a well-trained new energy prediction model.

[0063] In one embodiment, the historical data of new energy power generation includes at least historical data of photovoltaic power generation and historical data of wind power generation; the new energy prediction model may include at least a photovoltaic power generation prediction model and a wind power generation prediction model, and these two models are trained separately to obtain a trained photovoltaic power generation prediction model and a trained wind power generation prediction model.

[0064] Specifically, a smart photovoltaic (PV) power generation prediction model is trained with a daily granularity. Historical PV power generation data and related weather data are acquired, including daily PV power generation, weather conditions, temperature, and solar irradiance. Since the granularity is daily, data preprocessing is necessary, including outlier removal and interpolation to fill missing values. After preprocessing, relevant features are extracted, such as daily average temperature, maximum temperature, and minimum temperature from the weather data, and historical power generation trend features from the PV power generation data. The data is then divided into training and testing sets based on its generation time; the training set contains earlier-generation data, and the testing set contains later-generation data. The PV power generation prediction model is then trained using both the training and testing sets, resulting in a well-trained PV power generation prediction model.

[0065] Using the same method, a well-trained wind power generation prediction model can be obtained, enabling the prediction of wind power generation.

[0066] It should be noted that photovoltaic power generation prediction models and wind power generation prediction models can be built based on neural networks, support vector machines, or decision trees.

[0067] First, the relationship between the temperature control equipment's influence on the electrolytic cell's temperature change and time is obtained. Based on this relationship, the time required for the temperature to change from one temperature to another can be calculated. Changes in the electrolytic cell's power also correspond to changes in its temperature. By obtaining the relationship between temperature and power, once the specific power adjustment value is determined, the target temperature value for the electrolytic cell is known. Then, based on the current temperature conditions, the time required to adjust to the target temperature value can be calculated. Therefore, by predicting the electrolytic cell's electrical energy input, temperature control can be intervened in advance, making the temperature adjustment of the electrolytic cell more controllable.

[0068] In this embodiment of the invention, by predicting the power generation of new energy sources such as photovoltaics and wind power, the power generation of new energy sources (such as wind and solar power generation) for a future period of time is obtained from the current time period. The aforementioned electrolytic cell operation control is executed according to the predicted power generation of new energy sources. When it comes to the regulation of SOEC electrolytic cells, the target temperature value is obtained based on the target power value. Based on the time required for temperature change, temperature control can be intervened in advance so that the temperature field can start to change smoothly in advance, so as to quickly adapt to the changes in new energy power and achieve temperature and power adjustment near the predicted time point. Through more stable temperature control, the lifespan degradation of SOEC can be slowed down.

[0069] In step S200, when the power of the new energy source is less than the first power threshold, the electrolysis task is undertaken by PEMEC; the first power threshold is less than the maximum adjustable power of PEMEC.

[0070] Since the first power threshold is less than the maximum adjustable power of PEMEC, when the power of the renewable energy source is less than the first power threshold...

[0071] For example, the rated power of SOEC is 10kW, while the power adjustable range of PEMEC is 0~4.8kW. The maximum adjustable power of PEMEC is 4.8kW, and the first power threshold can be 4kW. The renewable energy power (such as wind and solar power) that the stack needs to absorb is renewable energy demand, which is less than 4kW. Of course, renewable energy demand is also less than the maximum adjustable power of PEMEC, 4.8kW. Therefore, PEMEC has a higher priority than SOEC, and PEMEC undertakes the electrolysis task.

[0072] In step S300, when the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold, SOEC and PEMEC jointly undertake the electrolysis task; the second power threshold is less than the sum of the maximum adjustable power of SOEC and PEMEC.

[0073] For example, the maximum adjustable power of SOEC can be 11KW, and the maximum adjustable power of PEMEC is 4.8KW. In the ideal case, the sum of their maximum adjustable powers is 15.8KW, the second power threshold can be 15KW, and the renewable energy generation power can be 11KW. At this time, SOEC and PEMEC jointly undertake the electrolysis task.

[0074] First, the PEMEC can be set to operate at 100-160% (the upper limit of the constraint), absorbing power fluctuations. For example, if the PEMEC absorbs 3.5kW of renewable energy power, its operating power is 3.5kW. The SOEC's operating power is the external renewable energy demand minus the renewable energy power absorbed by the PEMEC, resulting in an SOEC operating power of 7.5kW. In this case, because the fluctuating renewable energy power is absorbed by the PEMEC, the SOEC can operate at a relatively stable power level (e.g., 75% of its rated power, i.e., 7.5kW).

[0075] Generally, in order to extend the life of SOEC electrolyzers as much as possible, the stable operating power of SOEC is usually taken as 70% of its rated power; that is, the SOEC power is 70% of the operating power. It should be noted that in reality, the SOEC power is not completely kept at 70% of the rated power, but can fluctuate slightly around 70%, for example, within a range of 5%, that is, the stable operating power of SOEC can be 65%~75%.

[0076] According to the temperature-power curve of SOEC stacks, when the power of SOEC is maintained at 70% of its rated power, it means that the SOEC stack is in cooling mode relative to its rated power. Excessive temperature will promote the degradation of stack materials, etc. Lowering the temperature can appropriately slow down the degradation rate of SOEC stack materials.

[0077] In one embodiment, dynamically adjusting the operating power of the SOEC and PEMEC based on the voltage decay rate of the SOEC and a preset decay rate threshold includes:

[0078] When the voltage decay rate exceeds the preset decay rate threshold, the first transfer power in the SOEC's operating power is transferred to the PEMEC, and it continues to run for the first time.

[0079] When the voltage decay rate is less than the decay rate threshold, the second transfer power in the PEMEC's ​​operating power is transferred to the SOEC, and the second operation continues for a second time.

[0080] SOEC defines the lifetime extension effect of the first power transfer on SOEC as the first lifetime factor, while PEMEC defines the lifetime reduction effect of the second power transfer on SOEC as the second lifetime factor. The first lifetime factor is greater than the second lifetime factor.

[0081] In one embodiment, transferring a first transfer power from the SOEC's operating power to the PEMEC includes:

[0082] During the first switching time, the first transfer power in the SOEC's operating power is transferred to the PEMEC.

[0083] In one embodiment, transferring a second transfer power from the PEMEC's ​​operating power to the SOEC includes:

[0084] During the second switching time, the second transfer power from the PEMEC's ​​operating power is transferred to the SOEC.

[0085] Within a certain time period, power transfer can be performed based on the real-time degradation of the SOEC stack. The real-time degradation of the SOEC stack can be represented by the real-time voltage decay rate. Specifically, the voltage decay rate of the SOEC can be calculated according to equation (1):

[0086] (1)

[0087] in, The voltage decay rate of SOEC, This is the initial electrolysis voltage of SOEC. This is the actual electrolysis voltage of SOEC.

[0088] To maintain a constant hydrogen production, a higher electrolysis voltage is required. The voltage decay rate is a relative value; assuming a preset decay rate threshold of 0.2% / khr, when the voltage decay rate exceeds this value, the SOEC (Sodium Electrolytic Capacitor) is considered to be decaying too quickly. The greater the deviation of the actual SOEC voltage decay rate from this value, the faster the SOEC is decaying. In the SOEC's cooling operation mode, if the decay is too rapid, it switches to a low-temperature, low-power mode (e.g., operating at 70% of rated power); if the decay is very slow, it switches to a medium-high-temperature power mode (e.g., operating at 90% of rated power).

[0089] In this embodiment of the invention, the low-temperature switching of the SOEC is phased and periodic. Phased means that, provided the power fluctuations are borne by the PEMEC and the duration T is sufficiently long, the SOEC does not always switch to 70% power. Instead, it switches to the low-temperature mode within the range of 70%-90% based on the SOEC stack's degradation. Lower temperatures can slow down the SOEC's lifespan degradation, while higher temperatures are beneficial for higher electrolysis efficiency. Periodicity means that the switching within the 70%-90% range is cyclical.

[0090] The electrolysis duration T of the SOEC stack, which is responsible for the power fluctuations of new energy sources, is related to the stack's degradation. The faster the SOEC stack degrades, the more necessary it is to enter a low-temperature, low-power mode, which means a larger T is required. However, T cannot be too large, as prolonged exposure to low temperatures will significantly reduce the electrolysis efficiency of the SOEC. In other words, at least the following must be met: the sum of the lifespan extension effect and the electrolysis efficiency reduction effect of the low-temperature power mode of the SOEC stack should be greater than the lifespan reduction effect of the medium- and high-temperature power mode.

[0091] It should be noted that the effect of the low-temperature power mode of SOEC stack on reducing electrolysis efficiency can be converted into a reduction in lifetime.

[0092] Specifically, when the voltage decay rate of the SOEC exceeds a preset decay rate threshold, the first transfer power from the SOEC's operating power is transferred to the PEMEC, meaning the SOEC switches to a low-temperature, low-power mode. After the switch, the SOEC's operating power is typically around 70% of its rated power. Furthermore, after the first transfer power is transferred from the SOEC to the PEMEC, both the SOEC and PEMEC continue operating for an immediate period. For example, if 1kW of the first transfer power from the SOEC's 7.5kW operating power is transferred to the PEMEC, the SOEC's operating power becomes 6.5kW, and the PEMEC's ​​operating power becomes 4.5kW.

[0093] It should be noted that the high temperature mode and low temperature mode are relative values. For example, the normal operating temperature of an SOEC fuel cell stack is 750℃, and the low temperature operating mode is a value lower than the normal operating temperature, such as 650℃ or 600℃. The specific value should be determined based on the temperature and power curves of the fuel cell stack itself.

[0094] It can be understood that low temperature has an extension factor A for the lifespan of SOEC stacks, but low temperature also reduces the efficiency of the stack. The worse the efficiency, the earlier it will be phased out. Here, there can be a low temperature lifespan reduction factor B (which is negative). At the normal operating temperature of SOEC stacks, there is a normal lifespan decay factor C. In addition, it is also necessary to consider that the switching from high temperature to low temperature may also affect the lifespan of the stack. This effect may be positive or negative. Here, we assume that the lifespan impact factor is D. At the same time, the switching from low temperature to high temperature may also affect the lifespan of the stack. Here, we assume that the impact factor is E. When switching from high temperature to low temperature, there is a switching time T1 and a low temperature operation duration T2; at the same time, there is also a switching time T3 when switching from low temperature to high temperature. That is, the whole process of switching from high temperature to low temperature and then back to high temperature must satisfy equation (2):

[0095] (2)

[0096] Here, T1*D, ​​T2*A, etc., can be integrals, not necessarily a fixed value for D. It can be a value that changes over time, or it can be an average value. This value can be obtained empirically through multiple experiments based on the characteristics of the fuel cell system. Taking T1*D as an example, T1*D means the total change in the lifetime of the SOEC fuel cell when switching from a high temperature to a low temperature within the T1 time period.

[0097] In other words, once the switching temperature is determined, T1 and T3 are generally fixed based on the system's response speed, while T2 can be varied. By adjusting the value of T2, the lifespan decay of the SOEC stack is reduced within the overall time period of T1+T2+T3, that is, after the high-temperature stack switches to the low-temperature stack, which means the lifespan of the SOEC stack is extended.

[0098] Specifically, the slower the SOEC stack degrades, the weaker the need to enter the cryogenic mode. At this time, the effect of the cryogenic mode on extending the life of the SOEC stack (increasing life) and reducing efficiency (converted to reducing life) needs to be greater than the effect of the high-temperature mode on reducing the life of the SOEC stack (for example, greater than 3 times, etc., the multiple is adjustable, and the multiple is related to the life degradation of the specific stack). Among them, the effect of reducing efficiency in the cryogenic mode can be equivalent to reducing the life of the stack. Taking a common diesel engine as an example, the reduction in efficiency can be understood as the diesel engine degrading and the usable life reduced. Specifically, it can be expressed as equation (3):

[0099] (3)

[0100] Where S represents the reduced lifespan and P represents the efficiency reduction. This is the conversion factor (obtained based on accumulated experimental data).

[0101] It should be noted that, in this embodiment of the invention, the purpose of introducing the efficiency reduction effect of the low temperature mode is that if the life extension effect of the low temperature mode alone is greater than the life reduction effect of the high temperature mode, the fuel cell stack will be more likely to enter the low temperature mode, affecting the overall working efficiency of the fuel cell stack.

[0102] It should be noted that the lower the operating power of an SOEC stack, the lower its operating temperature and the lower its electrolysis efficiency.

[0103] In one embodiment, the first lifetime factor is:

[0104] After the SOEC transfers the first transfer power to the PEMEC, the operating temperature of the SOEC decreases. The effect of the temperature reduction on the life extension of the SOEC is called the life extension factor.

[0105] Lowering the temperature leads to a decrease in the electrolysis efficiency of SOEC. This decrease in electrolysis efficiency is converted into a reduction in the lifespan of SOEC, and the reduction in electrolysis efficiency on the lifespan of SOEC is called the lifespan reduction factor.

[0106] The first lifespan factor is the lifespan extension factor minus the lifespan reduction factor.

[0107] The power regulation method for hybrid power stacks provided in this invention combines SOEC and PEMEC, two different types of electrolyzers, to leverage the high electrolysis efficiency of SOEC and the fast start-up and good response of PEMEC. This allows for flexible response to renewable energy power while maintaining high electrolysis efficiency. A renewable energy prediction model is used to predict the renewable energy power generated. By predicting the input power to the electrolyzer, temperature control can be intervened in advance, making temperature adjustment of the electrolyzer more controllable. The specific electrolysis task scheme is determined based on the relationship between the renewable energy power and preset first and second power thresholds. When SOEC and PEMEC jointly undertake the electrolysis task, the operating power of SOEC and PEMEC is dynamically adjusted according to the real-time degradation of SOEC. This allows for dynamic adjustment of the stack's operating power based on changes in renewable energy power, ensuring the lifespan of the electrolyzer while keeping the SOEC stack operating within a safe and efficient power range. This ensures the safety of the stack, fully absorbs renewable energy power, avoids power curtailment, and improves the utilization rate of renewable energy.

[0108] Please see Figure 3 The present invention also provides an embodiment of a power regulation device for a hybrid fuel cell stack, wherein a solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series, and the power regulation device for the hybrid fuel cell stack includes:

[0109] The power prediction module 11 is used to predict the power of new energy generation using a trained new energy prediction model.

[0110] The first task module 22 is used to have the PEMEC undertake the electrolysis task when the power of the new energy source is less than a first power threshold; the first power threshold is less than the maximum adjustable power of the PEMEC.

[0111] The second task module 33 is used to have the SOEC and PEMEC jointly undertake the electrolysis task when the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC.

[0112] The dynamic adjustment module 44 is used to dynamically adjust the working power of the SOEC and the PEMEC according to the voltage decay rate of the SOEC and the preset decay rate threshold when the SOEC and the PEMEC jointly undertake the electrolysis task, so as to slow down the life decay rate of the SOEC while absorbing the new energy power.

[0113] The power regulation device for the hybrid stack provided in this invention combines SOEC and PEMEC, two different types of electrolyzers, in a mixed configuration. This leverages the high electrolysis efficiency of SOEC and the fast start-up and good response of PEMEC, enabling flexible response to renewable energy power while maintaining high electrolysis efficiency. By using a renewable energy prediction model to predict the renewable energy power generated, temperature control can be intervened in advance based on the predicted input power to the electrolyzer, resulting in greater controllability of the electrolyzer's temperature adjustment. The specific electrolysis task scheme is determined based on the relationship between the renewable energy power and preset first and second power thresholds. When SOEC and PEMEC jointly undertake the electrolysis task, the operating power of SOEC and PEMEC is dynamically adjusted according to the real-time degradation of SOEC. This allows for dynamic adjustment of the stack's operating power based on changes in renewable energy power, ensuring the lifespan of the electrolyzer while maintaining safe and efficient operation of the SOEC stack within a safe and efficient power range. This ensures stack safety, fully absorbs renewable energy power, avoids power curtailment, and improves the utilization rate of renewable energy.

[0114] In addition, the present invention also provides an electronic device, including: a processor and a memory;

[0115] The memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0116] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described.

[0117] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0118] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0121] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0122] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power regulation method for a hybrid fuel cell stack, characterized in that, A solid oxide electrolyzer (SOEC) and a proton exchange membrane electrolyzer (PEMEC) are connected in series. The power regulation method for the hybrid stack includes the following steps: Predict the power output of new energy generation using a trained new energy prediction model; When the power of the new energy source is less than the first power threshold, the electrolysis task is undertaken by the PEMEC; the first power threshold is less than the maximum adjustable power of the PEMEC. When the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold, the electrolysis task is jointly undertaken by the SOEC and the PEMEC; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC; When the SOEC and the PEMEC jointly undertake the electrolysis task, the working power of the SOEC and the PEMEC is dynamically adjusted according to the voltage decay rate of the SOEC and the preset decay rate threshold, so as to slow down the life decay rate of the SOEC while absorbing the new energy power. When the voltage decay rate is greater than the preset decay rate threshold, the first transfer power in the working power of the SOEC is transferred to the PEMEC and continues to run for a first time. When the voltage decay rate is less than the preset decay rate threshold, the second transfer power in the operating power of the PEMEC is transferred to the SOEC, and the operation continues for a second time. The SOEC defines the lifetime extension effect of the first power transfer on the SOEC as a first lifetime factor, and the PEMEC defines the lifetime reduction effect of the second power transfer on the SOEC as a second lifetime factor, wherein the first lifetime factor is greater than the second lifetime factor. The first lifetime factor is: After the SOEC transfers the first transfer power to the PEMEC, the operating temperature of the SOEC decreases, and the effect of the temperature reduction on the lifespan extension of the SOEC is the lifespan extension factor. The decrease in temperature leads to a decrease in the electrolysis efficiency of the SOEC. The decrease in the electrolysis efficiency of the SOEC is converted into a lifetime reduction effect on the SOEC. The lifetime reduction effect of the decrease in electrolysis efficiency on the SOEC is called the lifetime reduction factor. The first lifespan factor is the lifespan extension factor minus the lifespan reduction factor.

2. The power regulation method for the hybrid fuel cell stack according to claim 1, characterized in that, The step of transferring the first transfer power from the SOEC's operating power to the PEMEC includes: During the first switching time, the first transfer power in the working power of the SOEC is transferred to the PEMEC.

3. The power regulation method for the hybrid fuel cell stack according to claim 1, characterized in that, The step of transferring the second transfer power from the operating power of the PEMEC to the SOEC includes: During the second switching time, the second transfer power from the operating power of the PEMEC is transferred to the SOEC.

4. The power regulation method for the hybrid fuel cell stack according to claim 1, characterized in that, The voltage decay rate of the SOEC is calculated using the following formula: ； in, The voltage decay rate of SOEC, This is the initial electrolysis voltage of SOEC. This is the actual electrolysis voltage of SOEC.

5. The power regulation method for the hybrid fuel cell stack according to claim 1, characterized in that, Before using the trained new energy prediction model to predict the new energy power of new energy generation, the method further includes: Obtain historical data on new energy power generation within a preset time period; The historical data of new energy power generation is used to train the new energy prediction model, resulting in a well-trained new energy prediction model.

6. A power regulation device for a hybrid fuel cell stack, characterized in that, The power regulation device of the hybrid fuel cell stack adopts the power regulation method of the hybrid fuel cell stack as described in claim 1, wherein the solid oxide electrolyzer (SOEC) and the proton exchange membrane electrolyzer (PEMEC) are connected in series, and the power regulation device of the hybrid fuel cell stack includes: The power prediction module is used to predict the power of new energy generation using a trained new energy prediction model. The first task module is used to have the PEMEC undertake the electrolysis task when the power of the new energy source is less than a first power threshold; the first power threshold is less than the maximum adjustable power of the PEMEC. The second task module is used to have the SOEC and PEMEC jointly undertake the electrolysis task when the power of the new energy source is greater than or equal to the first power threshold and less than the second power threshold; the second power threshold is less than the sum of the maximum adjustable power of the SOEC and the PEMEC. The dynamic adjustment module is used to dynamically adjust the operating power of the SOEC and the PEMEC according to the voltage decay rate of the SOEC and the preset decay rate threshold when the SOEC and the PEMEC jointly undertake the electrolysis task, so as to slow down the life decay rate of the SOEC while absorbing the new energy power.

7. An electronic device, characterized in that, include: Processor and memory; The memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images