A selection method for hydrogen energy storage system electrolytic cell for complex multi-working conditions

Abstract

The application discloses a hydrogen energy storage system electrolytic cell selection method for complex multiple working conditions, comprising the following steps: according to existing large number platform data statistics results, determining different renewable energy hydrogen production scene probability distributions of various regions, multiple type electrolytic cell use probabilities and multiple type electrolytic cell use probabilities under different scenes, taking the data as input (prior probability matrix) of an electrolytic cell selection decision system, and then calculating electrolytic cell use probability matrix (posterior probability matrix) under different application service working conditions through a Bayesian estimation method according to the known prior probability. According to the dynamic correction of the Bayesian formula, the use probability of different types of electrolytic cells under different hydrogen production scenes is corrected, the multi-subject matching characteristics of the renewable energy hydrogen production and energy storage system are effectively ensured, the distribution problem of maximum resource utilization and maximum economic benefit in the renewable energy hydrogen production system is solved, and the economic construction of the hydrogen energy storage system applied to multiple types of scenes in the future can be effectively guaranteed.

Description

A method for selecting electrolyzers for hydrogen energy storage systems under complex and multi-condition operating conditions. Technical Field

[0001] This invention relates to an economic operation and management technology for renewable energy hydrogen production and storage systems, and more particularly to a method for selecting electrolyzers for hydrogen storage systems under complex and multi-condition conditions, based on data fusion theory for economic decision-making in electrolyzer selection. Background Technology

[0002] Under the goal of "peak carbon and carbon neutrality", the clean energy transition is an inevitable trend. The installed capacity of renewable energy is increasing rapidly. The best solution for the absorption of renewable energy and the resolution of its intermittency and volatility is undoubtedly to vigorously develop large-scale energy storage technology.

[0003] Due to the uneven geographical distribution of power generation on the load, the technological constraints of long-distance transmission, coupled with the inherent randomness, seasonality, and anti-peak-shaving characteristics of renewable energy generation, the difficulty of peak shaving for renewable energy is further increased. In addition, the significant unpredictability of wind and solar power contributes to the uneven distribution and unstable power generation of wind and solar power, creating difficulties for grid connection and leading to severe curtailment of wind, hydro, and solar power. Therefore, solving the problem of large-scale renewable energy consumption has become a crucial issue for achieving dual-carbon goals. Given the imbalance in renewable energy development and the volatility and intermittency of renewable energy sources such as wind and solar power, configuring energy storage systems is an effective means to address the current large-scale curtailment of wind and solar power. Developing new and efficient energy storage methods can not only further improve the flexibility of the power system but is also the most fundamental solution to the overcapacity of renewable energy generation.

[0004] Hydrogen energy, as one of the most promising energy sources for the future, is considered the "ultimate energy" of the 21st century due to its high calorific value, diverse sources, abundant reserves, and suitability for large-capacity, long-term storage. It also provides a new approach to large-scale energy storage technology. Therefore, for the large amounts of curtailed wind, solar, and hydropower resources with uneven distribution and intermittent characteristics, hydrogen energy is an ideal energy storage medium. Employing electricity-rich hydrogen production and storage technology can effectively solve the problems of renewable energy consumption and grid connection stability. By using electricity generated from curtailed wind and solar power to electrolyze water for hydrogen production, electricity-to-hydrogen conversion can be achieved, rationally utilizing curtailed wind and solar energy while smoothing out grid connection fluctuations of renewable energy, thus realizing the spatiotemporal transfer of energy.

[0005] The current mainstream technology for hydrogen production from renewable energy sources is water electrolysis. This involves feeding electricity generated from curtailed wind and solar power into an electrolyzer to produce hydrogen, which is then stored in storage tanks and other equipment for future hydrogen fuel cell power generation. Electrolyzers can be mainly classified into three types based on the electrolyte used: alkaline electrolyzers, proton exchange membrane electrolyzers, and solid oxide electrolyzers.

[0006] Given the large number of types of electrolyzers and their application service conditions, and the significant uncertainty in the probability of using various types of electrolyzers and their application scenarios due to the different distribution of renewable energy in different regions, it is crucial to select appropriate electrolyzers for hydrogen production within renewable energy distribution areas to maximize the economic benefits of the entire renewable energy electrolysis hydrogen production technology system. This will directly affect the economics of the renewable energy system, grid connection stability, and the service life of the electrolyzers.

[0007] The distribution and utilization rates of renewable energy vary across different regions, resulting in complex operating conditions for renewable energy electrolysis hydrogen production systems. Furthermore, the combination of new energy sources and hydrogen energy is diverse. Existing renewable energy hydrogen production systems struggle to comprehensively consider regional resource distribution differences and the need to maximize the economic benefits of using different types of electrolyzers in different hydrogen production scenarios, leading to significant resource waste and failure to maximize the utilization of surplus renewable energy power. In contrast, Bayesian decision-making methods can estimate the probability of some unknown data using subjective methods within incomplete existing big data, and then correct the posterior probability using the Bayesian formula. Finally, the optimal decision is made using the expected value and the corrected probability. In the process of continuously correcting the posterior probability, Bayesian decision-making methods avoid the overly subjective judgments of prior probabilities.

[0008] In view of this, the present invention is hereby proposed. Summary of the Invention

[0009] The purpose of this invention is to provide a method for selecting electrolyzers for hydrogen energy storage systems under complex and multi-condition operating conditions, so as to solve the above-mentioned technical problems existing in the prior art.

[0010] The objective of this invention is achieved through the following technical solution:

[0011] The present invention provides a method for selecting electrolyzers for hydrogen energy storage systems under complex and multi-condition operating conditions. This method uses a big data platform to analyze the distribution of renewable energy in different regions and the probability of using combined renewable energy hydrogen production equipment as input to the decision-making system. The method includes the following steps:

[0012] 1) Obtain prior probability distribution data of renewable energy hydrogen production scenarios in different regions of the country. Specific data include the probability of occurrence of different hydrogen production scenarios, the probability of use of different types of electrolyzers, and the probability of use of multiple types of electrolyzers under specific application service conditions.

[0013] 2) Input the existing data into the decision-making and selection system to calculate the posterior probability of use of the target object;

[0014] 3) Employing different application scenarios for electrolysis hydrogen production systems and considering the probability of use P(elec) of different types of electrolyzers. i ), 1≤i≤n, the probability of using different types of renewable energy electrolysis hydrogen production systems P(con j), 1≤j≤m and the conditional probability P(elec) of using multiple types of electrolytic cells under specific application conditions. i |con j The Bayesian estimation method is used to calculate the posterior probability of a renewable energy electrolysis hydrogen production system, and to obtain the posterior probability distribution of different electrolyzers applied to different hydrogen production scenarios.

[0015] 4) An economic benefit analysis method was adopted for selecting multiple types of electrolyzers under different hydrogen production scenarios based on inconsistent expert economic benefit calculation data, so as to obtain economic benefit data for different electrolyzers applied to different hydrogen production scenarios;

[0016] 5) Based on the posterior probability distribution of different electrolyzers in different hydrogen production scenarios, and considering the inconsistency of different experts' economic benefit calculation standards, DS data fusion technology is used to obtain the final solution that meets the decision-maker's preferences, namely the optimal economic selection scheme of the final electrolyzer under z kinds of expert economic benefit calculation data.

[0017] Compared with existing technologies, the Bayesian estimation-based electrolyzer selection method for hydrogen energy storage systems under complex multi-condition conditions provided by this invention is used for economic assessment and management of new energy + energy storage system construction. It fully considers the differences in regional resource distribution and the complexity of different scenarios for renewable energy electrolysis hydrogen production. It can effectively improve the economics of renewable energy electrolysis hydrogen production systems under multiple application service conditions, provide a technical reference for the large-scale application of renewable energy electrolysis hydrogen production systems in different regions, accelerate the application process of hydrogen energy in renewable energy consumption and smooth renewable energy fluctuations, and promote the realization of the "carbon peak and carbon neutrality" goal. Attached Figure Description

[0018] Figure 1 is a schematic diagram of the overall process of the electrolyzer selection method for hydrogen energy storage system under complex multi-operating conditions provided in an embodiment of the present invention;

[0019] Figure 2 is a block diagram of the Bayesian decision-making + data fusion comprehensive evaluation method proposed in this invention.

[0020] Figure 3 is a flowchart of the data fusion method used in this invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them, and do not constitute a limitation on the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0022] First, the following explanations are provided for the terms that may be used in this article:

[0023] The term "and / or" means that either or both can be achieved simultaneously. For example, X and / or Y means that it includes both "X" or "Y" as well as the three cases of "X and Y".

[0024] The terms “including,” “comprising,” “containing,” “having,” or other similar semantic descriptions should be interpreted as non-exclusive inclusion. For example, “including a technical feature element (such as raw material, component, ingredient, carrier, dosage form, material, size, part, component, mechanism, device, step, process, method, reaction conditions, processing conditions, parameter, algorithm, signal, data, product or article of manufacture, etc.)” should be interpreted as including not only the expressly listed technical feature element, but also other technical feature elements that are not expressly listed and are well-known in the art.

[0025] The term "composed of" excludes any technical features not expressly listed. When used in a claim, it closes the claim to exclude all technical features other than those expressly listed, except for associated conventional impurities. If the term appears only in a clause of a claim, it limits the claim to the elements expressly listed in that clause; elements recited in other clauses are not excluded from the overall claim.

[0026] The terms “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “back,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” and “counterclockwise” indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience and simplification of description and do not imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this document.

[0027] The contents not described in detail in the embodiments of this invention are prior art known to those skilled in the art. Where specific conditions are not specified in the embodiments of this invention, they shall be performed according to conventional conditions in the art or conditions recommended by the manufacturer. Where the manufacturers of the reagents or instruments used in the embodiments of this invention are not specified, they are all conventional products that can be purchased commercially.

[0028] The present invention provides a method for selecting electrolyzers for hydrogen energy storage systems under complex and multi-condition operating conditions. This method uses a big data platform to analyze the distribution of renewable energy in different regions and the probability of using combined renewable energy hydrogen production equipment as input to the decision-making system. The method includes the following steps:

[0029] 1) Obtain prior probability distribution data of renewable energy hydrogen production scenarios in different regions of the country. Specific data include the probability of occurrence of different hydrogen production scenarios, the probability of use of different types of electrolyzers, and the probability of use of multiple types of electrolyzers under specific application service conditions.

[0030] 2) Input the existing data into the decision-making and selection system to calculate the posterior probability of use of the target object;

[0031] 3) Employing different application scenarios for electrolysis hydrogen production systems and considering the probability of use P(elec) of different types of electrolyzers. i ), 1≤i≤n, the probability of using different types of renewable energy electrolysis hydrogen production systems P(con j ), 1≤j≤m and the conditional probability P(elec) of using multiple types of electrolytic cells under specific application conditions. i |con j The Bayesian estimation method is used to calculate the posterior probability of a renewable energy electrolysis hydrogen production system, and to obtain the posterior probability distribution of different electrolyzers applied to different hydrogen production scenarios.

[0032] 4) An economic benefit analysis method was adopted for selecting multiple types of electrolyzers under different hydrogen production scenarios based on inconsistent expert economic benefit calculation data, so as to obtain economic benefit data for different electrolyzers applied to different hydrogen production scenarios;

[0033] 5) Based on the posterior probability distribution of different electrolyzers in different hydrogen production scenarios, and considering the inconsistency of different experts' economic benefit calculation standards, DS data fusion technology is used to obtain the final solution that meets the decision-maker's preferences, namely the optimal economic selection scheme of the final electrolyzer under z kinds of expert economic benefit calculation data.

[0034] The following steps guide the selection of electrolyzers for different hydrogen production applications:

[0035] a) Let ELEC = (elec1, elec2, ..., con) n ) T Let the vectors represent different types of electrolyzers, namely AWE (Alkaline Water Electrolyzer), PEMEL (Proton Exchange Membrane Electrolyzer), SOEL (Solid Oxide Electrolyzer), etc.; and let CON(con1, con2, ..., con m ) T Vectors for hydrogen production scenarios based on different types of renewable energy sources;

[0036] b) Let the prior probabilities of various types of electrolytic cells be P(elec)i ), 1≤i≤n; the prior probability of hydrogen production scenarios for different types of renewable energy sources is P(con j ), 1≤j≤m;

[0037] c) The prior probabilities are obtained by using a big data analytics platform to acquire information on the usage of different types of electrolytic cells in a specific region across the country. In other words, the prior probabilities are derived from historical experience data, including electrolytic cell usage probability data. Prior probabilities of hydrogen production scenarios from different types of renewable energy sources P(elec i ) and P(con j ) is a category elec i and con j The prior probability, elec num and con num These are the sample numbers for electrolyzer category and hydrogen production scenario category, respectively, ELEC. N and CON N These are the total number of samples;

[0038] d) The conditional probability of using a certain type of electrolyzer under specific renewable energy hydrogen production application conditions is P(elec i |con j );

[0039] e) Determine the input parameter domain U of the Bayesian probability function, U = (P(elec i ), P(con j ), P(elec i |con j ));

[0040] f) The prior probabilities of different types of electrolyzers under different hydrogen production scenarios are obtained by correcting the prior probabilities using Bayes' theorem:

[0041]

[0042] g) Perform an economic evaluation on the posterior probability data from step f, where r represents the expert economic evaluation data, as shown in the following formulas:

[0043]

[0044] Where q ij (l) represents the system economic benefit evaluated by the l-th expert when the i-th electrolytic cell is applied to the j-th type of scenario, 1≤l≤r;

[0045] h) The economic evaluation results in step e are integrated using a data fusion method, and the final data is sorted to obtain the most economically optimal electrolytic cell selection scheme.

[0046] The Bayesian estimation method used in steps 2) and 3) to calculate the posterior probability estimates for different application conditions of the electrolyzer is expressed by the following formula:

[0047]

[0048] The economic benefit data fusion method described in step f uses z expert economic calculation data matrices as input for data fusion. The upper and lower limits of the z sets of data are set in the range of [0,1]. The output is the ranking result of the most economical application of each type of electrolyzer in different hydrogen production scenarios.

[0049] In summary, the electrolyzer selection method for hydrogen energy storage systems under complex multi-operating conditions in this invention addresses the shortcomings of existing technologies for the economic construction and optimized management of renewable energy hydrogen production and storage systems, as well as the stability issues of hydrogen energy storage systems during the grid-connected operation of renewable energy power generation. Based on better serving the economic construction of renewable energy hydrogen production and storage, improving regional resource matching, and optimizing system operation economy and stability, this invention proposes a Bayesian decision theory-based electrolyzer selection method for hydrogen energy storage systems under complex multi-operating conditions. This method utilizes historical experience data, including the distribution of renewable energy and the probability of use of various electrolyzers as statistically analyzed by a national big data platform, the probability of use of each type of electrolyzer (prior probability), the probability of application in different hydrogen production scenarios (prior probability), and the conditional probability of using a certain type of electrolyzer in a specific hydrogen production scenario. It then dynamically adjusts the probability of use of different types of electrolyzers in different hydrogen production scenarios using Bayesian formulas. This effectively ensures the multi-entity matching characteristics of renewable energy hydrogen production and storage systems, solves the problem of maximizing resource utilization and economic benefits in renewable energy hydrogen production systems, and can effectively guarantee the economic construction of future hydrogen energy storage systems applied to multiple scenarios.

[0050] This invention starts from the coupled operation characteristics of renewable energy power generation and electrolysis hydrogen production and storage systems, as well as the distribution of regional renewable energy resources. Based on big data analysis of the probabilities of different types of renewable energy hydrogen production scenarios in various regions, it employs a Bayesian estimation method that considers the differences in regional renewable energy distribution to complete the selection of electrolyzers under different application service conditions, aiming to maximize the economic benefits in the coupled operation of electrolyzer types with local renewable energy types. Specifically, it includes the following steps: Based on the statistical results of existing big data platforms, the probability distribution of different renewable energy hydrogen production scenarios in various regions, the probability of using multiple types of electrolyzers, and the probability of using multiple types of electrolyzers under different scenarios are determined. These data are used as the input (prior probability matrix) of the electrolyzer selection decision system. Then, based on the aforementioned known prior probabilities, the electrolyzer usage probability matrix (posterior probability matrix) under different application service conditions is calculated using the Bayesian estimation method. Three types of economic benefit calculation matrix data are used: conservative, aggressive, and moderate economic benefit calculation matrices. The economic benefit vector of a specific electrolyzer under different application scenarios is comprehensively calculated. Finally, the economic benefit vectors are fused and sorted to determine which type of electrolyzer is the most economically viable for hydrogen production under the current regional resource background.

[0051] This invention fully considers the differences in regional resource distribution and the complexity of different scenarios for renewable energy electrolysis hydrogen production. It can effectively improve the economics of renewable energy electrolysis hydrogen production systems under multiple application service conditions, provide a technical reference for the large-scale application of renewable energy electrolysis hydrogen production systems in different regions, accelerate the application process of hydrogen energy in renewable energy consumption and smooth renewable energy fluctuations, and promote the realization of the goal of "carbon peaking and carbon neutrality".

[0052] To more clearly demonstrate the technical solution and its effects provided by the present invention, the embodiments of the present invention will be described in detail below with reference to specific examples.

[0053] A method for selecting electrolyzers for hydrogen energy storage systems under complex multi-condition operating conditions, and an economic analysis method based on data fusion theory for different electrolyzer selections under various application service conditions. The method includes the following steps:

[0054] The historical data is corrected for posterior probabilities using the following process:

[0055] Let ELEC = (el e c1, elec2, ..., elec n ) TLet CON be the vectors for different types of electrolyzers, namely AWE (Alkaline Water Electrolyzer), PEMEL (Proton Exchange Membrane Electrolyzer), SOEL (Solid Oxide Electrolyzer), etc.; and let CON = (con1, con2, ..., elec m ) T Vectors for hydrogen production scenarios based on different types of renewable energy.

[0056] Let the prior probabilities of various types of electrolytic cells be P(elec) i ), 1≤i≤n; the prior probability of hydrogen production scenarios for different types of renewable energy sources is P(con j ), 1≤j≤m.

[0057] The posterior probability of a renewable energy electrolysis hydrogen production system was calculated, and the posterior probability distribution of different electrolyzers applied to different hydrogen production scenarios was obtained. The specific steps are as follows:

[0058] ①. Based on statistics from the national big data platform, calculate the required prior probability data: the probability of using different types of electrolytic cells, P(elec i The probability of hydrogen production scenarios P(con) j Furthermore, it is also necessary to calculate the conditional probabilities P(elec) of various electrolyzers under different hydrogen production scenarios. i |con j );

[0059] ②. Given that the various feature attributes in ①, such as the different types of electrolyzers and different hydrogen production scenarios, are conditionally independent, Bayes' theorem holds under this condition. Therefore, the posterior probability of the required feature attributes can be corrected using the following formula:

[0060]

[0061] ③. Obtain the posterior probability matrix of the feature attributes required for decision-making through Bayes' theorem, and conduct an economic evaluation of the use of electrolytic cells in each scenario;

[0062] ④. The economic evaluation process in ③ involves summarizing the posterior probability matrix data of the required feature attributes, integrating the posterior probability data with the economic calculation data, and calculating the economic benefits of a certain type of electrolyzer applied in different scenarios under the distribution of renewable energy in a specific region. This prepares for subsequent data screening and decision-making. The economic benefit data is obtained by the Hadamard product of the posterior probability data and the economic evaluation data.

[0063]

[0064] ⑤. Similarly, the economic evaluation data of each expert thereafter is calculated using formula ④ to obtain the economic benefit data of various types of electrolyzers under the specific hydrogen customization scenario;

[0065]

[0066] ⑥. Merge the economic benefit matrix obtained in step ⑤ by column to obtain comparative data on the economic benefits of each type of electrolyzer applied to different hydrogen production scenarios;

[0067] ⑦. Integrate the obtained economic evaluation data and use the DS data fusion method to obtain the economic benefit data vector of each type of electrolyzer in the specific hydrogen scenario;

[0068] ⑧. Sort the data obtained in ⑦ and determine the most suitable electrolyzer selection scheme for the hydrogen production scenario in the specified region.

[0069] The specific details and other features and advantages of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, many modifications and variations made by those skilled in the art based on the spirit of the present invention fall within the scope of protection of the present invention.

[0070] Example 1

[0071] As shown in Figures 1 to 3:

[0072] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when an element or component is referred to as “connected” to another element or component, it may be directly connected to the other element or component, or there may be intermediate elements or components. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items.

[0073] The renewable energy hydrogen production system described in this invention includes renewable energy power generation equipment such as wind and solar power, as well as energy storage equipment. The energy storage equipment mainly refers to the electrolyzer system. This invention mainly focuses on screening and deciding on the electrolyzer units in the renewable energy electrolysis hydrogen production system to ensure the highest degree of matching between the system construction and local resources and the best economic efficiency.

[0074] In this invention, the system input data for calculating the Bayesian probability function is obtained through the following method:

[0075] Step 1: Rely on a big data analytics platform to obtain the usage data of different types of electrolytic cells in a specific region across the country, i.e., obtain the corresponding prior probabilities through historical experience data, including electrolytic cell usage probability data. Prior probabilities of hydrogen production scenarios from different types of renewable energy sources P(elec i ) and P(con j ) is a category elec i and con j The prior probability, elec num and con num These are the sample numbers for electrolyzer category and hydrogen production scenario category, respectively, ELEC. N and CON N These represent the total number of samples.

[0076] Step 2: The conditional probability of using a certain type of electrolyzer under specific renewable energy hydrogen production application conditions is P(elec i |con j ), as shown in the example below:

[0077] Table 1

[0078]

[0079] Step 3: Input the data from Step 1 and Step 2 into the function that calculates the Bayesian probability.

[0080] Step 3, calculating the Bayesian probability function, includes the following steps:

[0081] Step 1. Let ELEC = (elec1, elec2, ..., elec...). n ) T Let CON be the vectors for different types of electrolyzers, namely AWE (Alkaline Water Electrolyzer), PEMEL (Proton Exchange Membrane Electrolyzer), SOEL (Solid Oxide Electrolyzer), etc.; and let CON = (con1, con2, ..., elec m ) T Vectors for hydrogen production scenarios based on different types of renewable energy sources;

[0082] Step 2. Let the prior probabilities of various types of electrolytic cells be P(ele) ci), 1≤i≤n; the prior probability of hydrogen production scenarios for different types of renewable energy sources is P(con j ), 1≤j≤m.

[0083] Step 3. The various characteristic attributes of different types of electrolyzers and different hydrogen production scenarios are conditionally independent. Under this condition, Bayes' theorem holds, so the posterior probability of the required characteristic attributes can be corrected using the following formula:

[0084]

[0085] Note: In the hydrogen production scenario, j and k do not interfere with each other.

[0086] Step 4. Obtain the posterior probability matrix of the feature attributes required for decision-making using Bayes' theorem, as shown in the following formula:

[0087]

[0088] Table 2

[0089]

[0090] The specific steps of the expert economic evaluation method in this invention are as follows:

[0091] a. First, for hydrogen production electrolyzer selection schemes under different application scenarios, extract the corresponding economic calculation database Q from the experts. l ;

[0092]

[0093] b. Integrate the posterior probability data with the economic calculation data to calculate the economic benefits of a certain type of electrolyzer applied in different scenarios under the distribution of renewable energy in a specific region, in order to prepare for subsequent data screening decisions. The economic benefit data is obtained by the Hadamard product (i.e., multiplying the corresponding elements of the matrix) of the posterior probability data and the economic evaluation data.

[0094]

[0095] c. Combine the economic benefit matrix obtained in step b by column to obtain comparative data on the economic benefits of applying electrolyzers to different hydrogen production scenarios, as shown in the table below:

[0096] Table 3

[0097]

[0098] d. Merge the m groups of vector data after column integration using DS data fusion technology. Refer to Figure 3 for the process. Input the data obtained in step c, assign a basic confidence level to each data vector, and fuse the data according to the Dempster merging rules to obtain the final electrolyzer decision logic.

[0099] Additional explanation: This invention is not limited to the number of indicators and the number of levels set in the above specific embodiments. Based on the technical solutions disclosed in this invention, those skilled in the art can make some substitutions and modifications to some of the technical features without creative labor, and these substitutions and modifications are all within the protection scope of this invention.

[0100] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. The information disclosed in the background section is intended only to enhance the understanding of the overall background technology of the present invention and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art.

Claims

1. A method for selecting an electrolyzer for a hydrogen energy storage system under complex multi-condition operating conditions, characterized in that, This method uses a big data platform to analyze the distribution of renewable energy in different regions and the probability of using renewable energy hydrogen production combined equipment as input to the decision-making and selection system. The steps include: 1) Obtaining prior probability distribution data of renewable energy hydrogen production scenarios in different regions of the country, specifically including the probability of occurrence of different hydrogen production scenarios, the probability of use of different types of electrolyzers, and the probability of use of multiple types of electrolyzers under specific application service conditions; 2) Inputting the existing data into the decision-making and selection system to calculate the posterior probability of use of the target object; 3) Using data based on different application scenarios of the electrolysis hydrogen production system and considering the probability of use of different types of electrolyzers. Probability of use of different types of renewable energy electrolysis hydrogen production systems And the conditional probability of using various types of electrolytic cells under specific application conditions. The Bayesian estimation method is used to calculate the posterior probability of the renewable energy electrolysis hydrogen production system, and the posterior probability distribution of different electrolyzers applied to different hydrogen production scenarios is obtained; 4) An economic benefit analysis method based on the inconsistency of expert economic benefit calculation data is adopted for the selection of multiple types of electrolyzers in different hydrogen production scenarios, and the economic benefit data of different electrolyzers applied to different hydrogen production scenarios is obtained; 5) For the posterior probability distribution of different electrolyzers applied to different hydrogen production scenarios, based on the inconsistency of different expert economic benefit calculation standards, DS data fusion technology is used to obtain the final solution that meets the decision-maker's preferences, i.e. The optimal economic selection scheme for the final electrolytic cell based on expert economic benefit calculation data; The following steps are used to select the appropriate electrolyzer for different hydrogen production applications: a) Setting up... Vectors for different types of electrolyzers: alkaline electrolyzer (AWE), proton exchange membrane electrolyzer (PEMEL), and solid oxide electrolyzer (SOEL); let CON (a) Vectors for hydrogen production scenarios using different types of renewable energy; (b) Let the prior probabilities of various electrolyzers be respectively... The prior probabilities of hydrogen production scenarios from different types of renewable energy sources are: c) Prior probabilities are obtained by using a big data analytics platform to acquire information on the usage of different types of electrolytic cells in a specific region across the country. This means that the corresponding prior probabilities are derived from historical experience data, including electrolytic cell usage probability data. Prior probabilities of hydrogen production scenarios from different types of renewable energy sources ， and It is a category and The prior probability, and These represent the sample size for electrolyzer type and hydrogen production scenario type, respectively. and These are the total number of samples; d) the conditional probability of using a certain type of electrolyzer under specific renewable energy hydrogen production application conditions is... e) Determine the input parameter domain of the Bayesian probability function. ， ； f) The prior probabilities of different types of electrolyzers under different hydrogen production scenarios are obtained by correcting the prior probabilities using Bayes' theorem: g) Evaluate the economic viability of the posterior probability data from step f. The expert economic evaluation data are shown in the following formulas: ;in For the first The medium electrolytic cell is used in the first The first type of scenario The system's economic benefits were assessed by several experts. h) The economic evaluation results from step e) are unified and integrated using a data fusion method, and the final data is sorted to obtain the most economically optimal electrolyzer selection scheme; The Bayesian estimation method for calculating the posterior probability in steps 2) and 3) estimates the posterior probability for different application conditions of the electrolyzer using the following formula: In step 5), A matrix of expert economic calculation data is used as input for data fusion. The upper and lower limits of the data set are set in the range of [0,1]. The output is the ranking of the most economical electrolyzers for different hydrogen production scenarios.

Images