Operating scheme prediction method and apparatus for fuel cell system, and computer device

Abstract

The present application relates to an operating scheme prediction method and apparatus for a fuel cell system, a computer device, a computer readable storage medium, and a computer program product. The method comprises: acquiring a preset operating parameter item of a fuel cell system to be predicted, and acquiring a preset value range and a preset value precision of the preset operating parameter item; on the basis of the preset value range and the preset value precision, randomly generating a plurality of operating parameter values of the preset operating parameter item; respectively converting the operating parameter values into genetic information of individuals in a genetic algorithm to obtain an initial population; and acquiring preset constraint condition information and a plurality of preset objective functions, and on the basis of a preset constraint condition, the preset objective functions, and the initial population, obtaining a predicted operating scheme of said fuel cell system. The use of the method can improve the efficiency of predicting an operating scheme of the fuel cell system.

Description

Methods, devices, and computer equipment for predicting the operation scheme of fuel cell systems Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for predicting the operation scheme of a fuel cell system. Background Technology

[0002] In the research and application of fuel cell systems, the performance parameters of the fuel cell system, such as current density, hydrogen utilization rate, system efficiency and durability, directly determine its technological advancement and market competitiveness.

[0003] However, traditional optimization methods typically rely on simulation testing. As an alternative, simulation testing usually involves simply dividing each parameter evenly and combining the calculations, failing to fully consider the differences in the impact of different parameters on system performance and economy. This increases the unnecessary computational burden, resulting in low optimization efficiency and poor efficiency predictions for fuel cell system operation schemes. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for predicting fuel cell system operation schemes that can improve the prediction efficiency of fuel cell system operation schemes, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for predicting the operation scheme of a fuel cell system, including:

[0006] Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range and preset value precision of the preset operating parameters;

[0007] Based on the preset value range and preset value precision, multiple sets of operating parameter values ​​for the preset operating parameter items are randomly generated;

[0008] Each of the aforementioned operating parameter values ​​is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population;

[0009] Obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

[0010] In one embodiment, the step of converting each of the running parameter values ​​into the genetic information of an individual in the genetic algorithm includes:

[0011] The encoding length corresponding to the preset running parameter item is determined based on the preset value range and preset value precision;

[0012] Based on the encoding length, determine the encoding relationship of the preset running parameter items;

[0013] Based on the encoding relationship, each of the running parameter values ​​is converted into encoded information, which serves as the genetic information of an individual in the genetic algorithm.

[0014] In one embodiment, obtaining the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each of the preset objective functions, and the initial population includes:

[0015] Based on the preset constraints and the preset objective functions, the fitness functions of individuals in multiple genetic algorithms are obtained;

[0016] Using the initial population as the current population, calculate the fitness of each individual in the current population;

[0017] Based on the fitness and the current population, a offspring population is generated, and the offspring population is used as the new current population. The process of calculating the fitness of each individual in the current population is then repeated until an offspring population that meets the preset conditions is obtained.

[0018] Based on the offspring population that meets the preset conditions, a predictive operation scheme for the fuel cell system to be predicted is determined.

[0019] In one embodiment, generating a offspring population based on the fitness and the current population includes:

[0020] Based on the fitness, individuals in the current population are sorted by non-dominance to determine the non-dominance level of each individual in the current population; each non-dominance level contains at least one individual.

[0021] From the current population, remove the individual with the lowest non-dominant level to obtain the parent population;

[0022] The offspring population is generated based on the parent population.

[0023] In one embodiment, generating the offspring population based on the parent population includes:

[0024] Based on the parent population, the first offspring population is obtained through crossover and mutation operations;

[0025] Calculate the crowding distance of the individual with the highest non-dominant level in the parent population;

[0026] Based on the crowding distance, a predetermined number of individuals are selected from the individuals with the highest non-dominant level in the parent population and integrated into the second offspring population.

[0027] The first and second offspring populations together constitute the offspring population.

[0028] In one embodiment, calculating the fitness of each individual in the current population includes:

[0029] In a physical simulation tool, a simulation model of the fuel cell system to be predicted is constructed;

[0030] In the physical simulation tool, the fitness of each individual in the current population is calculated based on the simulation model;

[0031] The step of generating a offspring population based on the fitness and the current population includes:

[0032] An optimized prediction tool is used to generate a offspring population based on the fitness and the current population.

[0033] Secondly, this application also provides a fuel cell system operation scheme prediction device, comprising:

[0034] The information acquisition module is used to acquire preset operating parameters of the fuel cell system to be predicted, as well as the preset value range and preset value precision of the preset operating parameters.

[0035] The parameter generation module is used to randomly generate multiple sets of operating parameter values ​​for the preset operating parameter items based on the preset value range and preset value precision.

[0036] The gene conversion module is used to convert each of the above-mentioned running parameter values ​​into the gene information of individuals in the genetic algorithm to obtain the initial population;

[0037] The scheme prediction module is used to acquire preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each of the preset objective functions and the initial population.

[0038] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0039] Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range and preset value precision of the preset operating parameters;

[0040] Based on the preset value range and preset value precision, multiple sets of operating parameter values ​​for the preset operating parameter items are randomly generated;

[0041] Each of the aforementioned operating parameter values ​​is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population;

[0042] Obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0044] Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range and preset value precision of the preset operating parameters;

[0045] Based on the preset value range and preset value precision, multiple sets of operating parameter values ​​for the preset operating parameter items are randomly generated;

[0046] Each of the aforementioned operating parameter values ​​is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population;

[0047] Obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0049] Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range and preset value precision of the preset operating parameters;

[0050] Based on the preset value range and preset value precision, multiple sets of operating parameter values ​​for the preset operating parameter items are randomly generated;

[0051] Each of the aforementioned operating parameter values ​​is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population;

[0052] Obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

[0053] In the above-mentioned method for predicting the operation scheme of fuel cell system, firstly, the preset operating parameters of the fuel cell system to be predicted are obtained, as well as the preset value range and preset value precision of the preset operating parameters. By obtaining the preset operating parameters and their value range and precision, it is ensured that the optimization process can be carried out based on real system operating data and boundary conditions, thus guaranteeing the effectiveness and accuracy of the entire optimization process, and also reflecting the actual operating state of the system through precise values. This precision setting avoids affecting the accuracy of optimization results due to overly coarse or insufficiently refined parameter values, ensuring the feasibility and stability of the generated operating scheme in practice. Next, based on the preset value range and preset precision, multiple sets of operating parameter values ​​are randomly generated for the preset operating parameter items. Randomly generating multiple sets of operating parameter values ​​increases the diversity of system parameter combinations, avoiding the parameter limitations caused by simple uniform partitioning in traditional simulation methods. This allows for coverage of a wider solution space, helping to explore the system performance under different parameter combinations, improving the comprehensiveness of the optimization process and the diversity of the final solution. Simultaneously, the precision setting effectively avoids unnecessary computational burden, reducing suboptimal solutions caused by excessively low precision and overcomputation caused by excessively high precision. Then, each operating parameter value is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population, and the operating parameter values ​​are converted into genetic algorithm values. The genetic algorithm generates an initial population by extracting genetic information, providing an effective encoding method. This allows the genetic algorithm to generate new parameter combinations using genetic operations such as crossover and mutation, and gradually optimize the solution through an evolutionary process. Finally, it obtains preset constraint information and multiple preset objective functions. Based on the preset constraints, objective functions, and the initial population, it obtains the predicted operation scheme of the fuel cell system to be predicted. During the optimization process, the genetic algorithm combines the preset constraints and multiple objective functions, enabling it to adaptively adjust the evolutionary direction and concentrate resources on key parameters that have a significant impact on performance and economy. Therefore, during the iteration process, the changes in parameters with a smaller impact on system performance gradually decrease, thereby reducing the computational requirements for these minor parameters and improving the algorithm's efficiency. Through fitness evaluation, suboptimal solutions are gradually eliminated, and resources are concentrated on more promising solutions, avoiding the inefficient process of calculating all parameters equally. In the above method, the selective optimization mechanism of the genetic algorithm can gradually eliminate solutions that do not meet the objectives, avoiding indiscriminate calculations for every parameter combination. Compared to the uniform partitioning in traditional methods, the genetic algorithm, by considering the precision of each preset operating parameter value, gradually reduces the focus on minor parameters through selection, crossover, and mutation during the evolutionary process, concentrating on optimizing key parameters and significantly reducing unnecessary computational burden. Ultimately, this improves the prediction efficiency of fuel cell system operation schemes and the utilization rate of computing resources, enabling the entire optimization process to maintain accuracy while achieving higher computational efficiency. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 is a flowchart illustrating a method for predicting the operation scheme of a fuel cell system in one embodiment;

[0056] Figure 2 is a flowchart illustrating the steps for obtaining a predicted operating plan in one embodiment;

[0057] Figure 3 is a flowchart illustrating the fuel cell system operation scheme prediction method in another embodiment;

[0058] Figure 4 is a schematic diagram of a fuel cell system to be predicted in one embodiment;

[0059] Figure 5 is a flowchart illustrating a method for predicting the operation scheme of a fuel cell system in one embodiment;

[0060] Figure 6 is a structural block diagram of a fuel cell system operation scheme prediction device in one embodiment;

[0061] Figure 7 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] In one embodiment, as shown in Figure 1, a method for predicting the operation scheme of a fuel cell system is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0064] In this embodiment, the method includes the following steps:

[0065] Step S101: Obtain the preset operating parameters of the fuel cell system to be predicted, as well as the preset value range and preset value accuracy of the preset operating parameters.

[0066] Among them, the preset operating parameters refer to the parameters that affect the performance, economy and other key factors of the fuel cell system during operation. These parameters typically include current density, operating temperature, inlet temperature, water-to-carbon ratio, and basic fuel cell parameters such as number of cells and flow channel size. These parameters play an important role in the design and optimization of the system.

[0067] The preset value range refers to the range of possible values ​​for each running parameter in actual operation. It is used to limit the exploration range of each parameter during the optimization process, ensuring that the calculation results are within a reasonable physical and engineering range. The preset value precision refers to the minimum unit change or allowable numerical precision required for the running parameter in the system. It affects the fineness of the parameter representation during the optimization process and determines the calculation accuracy of the algorithm and the degree of refinement of the solution.

[0068] For example, when obtaining preset operating parameters of a fuel cell system, the terminal extracts these parameters from system design documents, experimental data, or existing system operating history. For each parameter, the terminal also obtains its preset value range and accuracy. For instance, for the current density parameter, the value range might be 0 to 100 A / cm². 2 The accuracy of the value may be 0.01 A / cm. 2 The parameter range for hydrogen utilization rate can be from 50% to 90%, with a precision of 0.1%. This range and precision ensure that the generated parameter values ​​in subsequent optimization calculations not only conform to the actual operation of the physical system but also achieve the required computational accuracy, thus avoiding problems with overly coarse or overly fine numerical representations during the optimization process.

[0069] Step S102: Based on the preset value range and preset value precision, randomly generate multiple sets of operating parameter values ​​for the preset operating parameter items.

[0070] Among them, the running parameter values ​​refer to the specific values ​​of each set of parameter items generated according to the preset value range and preset value precision, which are used for individual gene expression in subsequent genetic algorithms.

[0071] For example, the terminal randomly generates multiple sets of operating parameter values ​​using a random number generation algorithm or Monte Carlo method, based on the preset value range and precision of each parameter. The generation process considers the upper and lower limits of each parameter and discretizes the parameters according to the precision requirements. For example, if the current density ranges from 0 to 100 A / cm²... 2 The accuracy is 0.01A / cm. 2The terminal generates a random number between 0 and 100 with two decimal places as the value of the parameter. Similarly, if the hydrogen utilization rate ranges from 50% to 90% with a precision of 0.1%, the parameter value generated by the terminal will take values ​​within this range in 0.1% increments. This generation method ensures that each parameter value varies within a reasonable range and meets specific precision requirements.

[0072] Step S103: Convert each running parameter value into the gene information of an individual in the genetic algorithm to obtain the initial population.

[0073] In genetic algorithms, gene information is the encoded representation of an individual. Encoding operations convert each parameter value into a gene representation that the algorithm can process. The initial population is the first-generation solution set of the genetic algorithm, containing multiple individuals, each represented by a set of gene information, and serving as the starting point for the optimization process.

[0074] For example, after acquiring multiple sets of operating parameter values, the terminal converts these values ​​into genetic information for the genetic algorithm using specific encoding rules (e.g., binary encoding, real number encoding, or other suitable problem encoding forms). The terminal first determines the encoding method for each operating parameter item, ensuring that the value of each parameter item can be processed using a unified genetic expression method. For instance, for continuous parameters such as current density, the terminal can convert them into real number encoding, or use binary encoding for discrete parameters. Each set of converted genetic information is combined to form individuals representing the operating scheme of the fuel cell system, thus forming the initial population. The diversity of the initial population provides a rich solution space for subsequent genetic operations (such as selection, crossover, and mutation), helping the genetic algorithm effectively explore the optimal solution.

[0075] Step S104: Obtain preset constraint information and multiple preset objective functions. Based on the preset constraints, each preset objective function and the initial population, obtain the predicted operation scheme of the fuel cell system to be predicted.

[0076] Among these, the preset constraint information refers to the physical, engineering, or economic limitations that the fuel cell system must meet during operation, such as boundary conditions like temperature, pressure, and fuel utilization rate. The preset objective function consists of multiple performance indicators used to measure the optimization results, typically involving aspects such as system efficiency, economy, and durability.

[0077] For example, the terminal first acquires the constraint information of the fuel cell system to ensure that each parameter combination meets basic operational limitations during operation. For instance, constraints might include temperature differences between heat exchangers. Then, the terminal acquires multiple preset objective functions to evaluate the performance of each individual, which may include multi-objective functions such as maximizing system efficiency, minimizing fuel consumption, or minimizing cost. The terminal calculates the fitness of each individual by comparing it to these objective functions and constraints in the initial population, and iteratively optimizes the population using a genetic algorithm. Based on the fitness value, the terminal selects individuals with better performance for genetic operations (such as selection, crossover, and mutation) to generate a new generation of individuals, continuously updating the population. After several generations of iterative optimization, the terminal finally selects individuals that satisfy all constraints and perform well on multiple preset objective functions, outputting this as the predicted operating scheme.

[0078] In the above-mentioned method for predicting the operation scheme of fuel cell system, firstly, the preset operating parameters of the fuel cell system to be predicted are obtained, as well as the preset value range and preset value precision of the preset operating parameters. By obtaining the preset operating parameters and their value range and precision, it is ensured that the optimization process can be carried out based on real system operating data and boundary conditions, thus guaranteeing the effectiveness and accuracy of the entire optimization process, and also reflecting the actual operating state of the system through precise values. This precision setting avoids affecting the accuracy of optimization results due to overly coarse or insufficiently refined parameter values, ensuring the feasibility and stability of the generated operating scheme in practice. Next, based on the preset value range and preset precision, multiple sets of operating parameter values ​​are randomly generated for the preset operating parameter items. Randomly generating multiple sets of operating parameter values ​​increases the diversity of system parameter combinations, avoiding the parameter limitations caused by simple uniform partitioning in traditional simulation methods. This allows for coverage of a wider solution space, helping to explore the system performance under different parameter combinations, improving the comprehensiveness of the optimization process and the diversity of the final solution. Simultaneously, the precision setting effectively avoids unnecessary computational burden, reducing suboptimal solutions caused by excessively low precision and overcomputation caused by excessively high precision. Then, each operating parameter value is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population, and the operating parameter values ​​are converted into genetic algorithm values. The genetic algorithm generates an initial population by extracting genetic information, providing an effective encoding method. This allows the genetic algorithm to generate new parameter combinations using genetic operations such as crossover and mutation, and gradually optimize the solution through an evolutionary process. Finally, it obtains preset constraint information and multiple preset objective functions. Based on the preset constraints, objective functions, and the initial population, it obtains the predicted operation scheme of the fuel cell system to be predicted. During the optimization process, the genetic algorithm combines the preset constraints and multiple objective functions, enabling it to adaptively adjust the evolutionary direction and concentrate resources on key parameters that have a significant impact on performance and economy. Therefore, during the iteration process, the changes in parameters with a smaller impact on system performance gradually decrease, thereby reducing the computational requirements for these minor parameters and improving the algorithm's efficiency. Through fitness evaluation, suboptimal solutions are gradually eliminated, and resources are concentrated on more promising solutions, avoiding the inefficient process of calculating all parameters equally. In the above method, the selective optimization mechanism of the genetic algorithm can gradually eliminate solutions that do not meet the objectives, avoiding indiscriminate calculations for every parameter combination. Compared to the uniform partitioning in traditional methods, the genetic algorithm, by considering the precision of each preset operating parameter value, gradually reduces the focus on minor parameters through selection, crossover, and mutation during the evolutionary process, concentrating on optimizing key parameters and significantly reducing unnecessary computational burden. Ultimately, this improves the prediction efficiency of fuel cell system operation schemes and the utilization rate of computing resources, enabling the entire optimization process to maintain accuracy while achieving higher computational efficiency.

[0079] In an exemplary embodiment, step S103, which converts each running parameter value into the genetic information of an individual in the genetic algorithm, further includes: determining the encoding length corresponding to a preset running parameter item based on a preset value range and a preset value precision; determining the encoding relationship of the preset running parameter item based on the encoding length; and converting each running parameter value into encoding information based on the encoding relationship, which serves as the genetic information of an individual in the genetic algorithm.

[0080] For example, the terminal first determines the corresponding encoding length based on the value range and precision of each preset operating parameter. For instance, if a certain operating parameter has a value range of 0 to 100 and a precision of 0.01, the terminal will need sufficient bits to represent each possible value between 0 and 100. This means that the encoding length for this parameter may need to be relatively long to ensure that all precise values ​​can be represented. Next, the terminal determines the encoding relationship of the parameter based on the encoding length. For some parameters, binary encoding can be used to convert the numerical value into a corresponding binary bit string; while for continuous parameters with high precision requirements, real number encoding may be used. The terminal converts each operating parameter value into corresponding encoded information according to the encoding relationship, thereby generating the individual's genetic information. This information will serve as the individual's genetic representation in the genetic algorithm and participate in subsequent optimization processes.

[0081] In this embodiment, by determining the encoding length based on the value range and precision of each parameter, the accurate expression of different parameter terms is ensured. This allows the optimization step size of parameters in the genetic algorithm to be flexibly adjusted according to their importance to the system. This not only avoids the uniform processing of all parameters in traditional uniform parameter tuning methods but also enables more effective optimization based on the different characteristics of each parameter. For critical parameters, a smaller encoding step size ensures fine-tuning, while for minor parameters with less influence, a larger step size accelerates the optimization process and reduces unnecessary computational burden. Ultimately, this optimization method improves the efficiency and accuracy of fuel cell system operation scheme prediction, enabling the system to converge to the optimal solution faster and more accurately.

[0082] In an exemplary embodiment, step S101 above, which obtains the preset value range and preset value precision of the preset operating parameter item, further includes: performing sensitivity analysis on each preset operating parameter item to obtain analysis results; and determining the preset value precision corresponding to each preset operating parameter item based on the analysis results.

[0083] For example, after obtaining the value ranges of each preset operating parameter, the terminal first performs a sensitivity analysis on each parameter. By adjusting the value of each parameter, the terminal observes its impact on the performance of the fuel cell system (such as efficiency, lifespan, or cost), thereby determining which parameters have a significant impact on the results and which have a smaller impact. For example, if the change in current density has a significant impact on system efficiency, then this parameter requires a higher value accuracy to ensure fine-tuning during the optimization process. For parameters with a smaller impact, such as certain environmental condition variables, a lower value accuracy can be used to avoid excessive computational burden. Based on the results of the sensitivity analysis, the terminal determines the preset value accuracy for each parameter. For example, the value accuracy of current density can be set to 0.01 A / cm. 2 This ensures high-precision adjustments during optimization, with the accuracy of hydrogen utilization potentially set to 0.1% to reduce computational overhead. In this way, highly sensitive parameters achieve higher precision, while less sensitive parameters can be optimized with lower precision, thereby improving the overall computational efficiency of the system.

[0084] In this embodiment, by performing sensitivity analysis on each preset operating parameter and adjusting the precision of the values ​​based on the analysis results, computational resources can be rationally allocated according to the importance of each parameter. Sensitivity analysis ensures that key parameters are precisely adjusted during the optimization process to improve system performance and the accuracy of optimization results. Simultaneously, for minor parameters with minimal impact on the system, reducing their precision decreases unnecessary computational burden and optimizes the efficiency of system resource utilization. This not only accelerates the optimization speed of the fuel cell system operation scheme but also improves the accuracy and reliability of the overall prediction scheme.

[0085] In an exemplary embodiment, as shown in FIG2, the above step S104, based on preset constraints, preset objective functions, and an initial population, obtains the predicted operation scheme of the fuel cell system to be predicted. This can also be achieved through the following steps:

[0086] Step S201: Based on the preset constraints and preset objective functions, obtain the fitness functions of individuals in multiple genetic algorithms;

[0087] Step S202: Using the initial population as the current population, calculate the fitness of each individual in the current population;

[0088] Step S203: Based on fitness and the current population, generate a child population, use the child population as the new current population, and return to the step of calculating the fitness of each individual in the current population until a child population that meets the preset conditions is obtained.

[0089] Step S204: Determine the predicted operation scheme of the fuel cell system to be predicted based on the offspring population that meets the preset conditions.

[0090] For example, the terminal first defines a fitness function based on each preset objective function and constraint. Each fitness function reflects an individual's performance on the objective function and ensures that all solutions satisfy the basic constraints. For instance, if the system requires maximizing efficiency and minimizing cost, the fitness function can include both objectives simultaneously and penalize individuals that violate the constraints, thus ensuring that individuals always meet the basic operating limits. This treats the constraints as a separate objective; if the constraints are not met, the fitness corresponding to that objective will be extremely low, and if they are met, the fitness will be extremely high. Then, the terminal calculates the fitness function for each individual in the initial population, evaluating each individual's performance on the objective function. The result is the fitness value of each individual, which measures its performance in multi-objective optimization. For example, an individual with a high fitness value may represent higher system efficiency and lower cost, meeting the preset objectives. Next, the terminal selects from the current population based on each individual's fitness value and generates offspring through crossover and mutation operations in a genetic algorithm. The selection operation tends to choose individuals with higher fitness, giving them a greater probability of participating in the generation of the next generation, thereby gradually eliminating unfit individuals. After the offspring population is generated, the terminal uses it as the new current population and repeats the step of calculating the fitness of each individual until an optimal solution that meets preset conditions is found. This process continues until a set stopping condition is reached (such as convergence of fitness values ​​or the maximum number of iterations). Once the terminal obtains the optimal offspring population that meets the preset objective function and constraints through multiple generations of iterations, it uses this as the final solution set and selects the final operating scheme from it as the operating scheme for the fuel cell system to be predicted. This scheme maximizes performance or economy while satisfying system constraints, ultimately providing a valuable reference for the actual operation of the fuel cell system.

[0091] The final operating scheme is selected from the final solution set. Specifically, since there are multiple objective functions, different solutions may perform differently on different objectives. Therefore, there is no single "optimal solution," but rather a Pareto front, i.e., a set of solutions, where each solution is not dominated by other solutions on one or more objectives. Then, by assigning different weights to each objective function, a weighted sum of each solution is calculated. The solution with the smallest (or largest) weighted sum is then selected as the final scheme from the Pareto optimal solution set. Alternatively, solutions can be selected based on the priority of a specific objective according to user needs. Another approach is to define the ideal value (i.e., the optimal value of the objective function) of multiple objective functions as an ideal point, calculate the distance from each solution to this ideal point, and select the solution with the shortest distance as the final scheme.

[0092] In this embodiment, the above steps effectively utilize the iterative optimization mechanism of the genetic algorithm to progressively select the optimal operating scheme for the fuel cell system. By generating a progeny population through multiple iterations and calculating its fitness, the system can progressively optimize the solution set under multi-objective constraints. The final solution satisfies the constraints and performs excellently on multiple performance objectives. This method not only improves the optimization efficiency of the system but also ensures the accuracy and reliability of the final solution.

[0093] In an exemplary embodiment, step S203, which generates a child population based on fitness and the current population, further includes: sorting individuals in the current population by non-dominance based on fitness to determine the non-dominance level of each individual in the current population; each non-dominance level contains at least one individual; removing the individual with the lowest non-dominance level from the current population to obtain the parent population; and generating a child population based on the parent population.

[0094] Non-dominated ranking refers to dividing individuals in a population into different tiers based on their performance on multiple objective functions.

[0095] In this context, the non-dominated hierarchy represents the ranking of each individual in the population. Individuals at higher levels perform better and are not dominated by other individuals in all goals.

[0096] For example, the terminal first performs a non-dominated ranking of all individuals in the current population. The principle of non-dominated ranking is as follows: the first tier (i.e., individuals at the highest non-dominated level) includes all individuals that are not completely dominated by other individuals on any objective; that is, these individuals perform well on one or more objectives. The second tier includes individuals that are not dominated by the remaining individuals after individuals in the first tier are removed, and so on. In this way, the terminal can divide the individuals in the population into multiple tiers according to the non-dominated ranking, with individuals in each tier possessing similar levels of excellence. Individuals in each non-dominated tier are ranked according to their multi-objective fitness. The terminal assigns these individuals to different tiers, with individuals in non-dominated tier 1 performing best, individuals in non-dominated tier 2 performing second best, and so on. These tiers are used to guide the selection and elimination of individuals, ensuring that individuals with excellent performance are preferentially retained during evolution. Based on fitness and non-dominated tier ranking, the terminal removes individuals with the lowest non-dominated tier in the current population. These individuals perform poorly on all objectives and are therefore not retained in the next generation of the population. By removing individuals from the lowest level, the overall quality of the population can be effectively improved, retaining individuals that perform well on multiple objectives. After removing poorly performing individuals, the remaining parent population is used to generate a new offspring population. The offspring generation process includes the following steps: Selection: Selection is performed based on parent individuals with higher non-dominant levels, prioritizing individuals with better fitness. Crossover: Crossover operations are performed between parent individuals to generate new individuals. The crossover operation incorporates the genetic information of the parent individuals, making it possible for offspring individuals to exhibit superior traits. Mutation: Mutation operations are performed on some offspring individuals to introduce new gene combinations, ensuring population diversity and avoiding getting trapped in local optima. The generated offspring population will serve as the new current population and continue to participate in the next round of iteration optimization.

[0097] In this embodiment, by performing a non-dominated sort on the current population, the superiority or inferiority of individuals can be effectively distinguished, and a suitable parent population can be selected based on their non-dominated level. Removing poorly performing individuals not only improves the overall quality of the population but also generates a more diverse and promising offspring population through crossover and mutation operations. Ultimately, this helps the genetic algorithm find the optimal solution more quickly in multi-objective optimization problems. This ensures that the genetic algorithm can balance multiple objectives during the optimization process, gradually selecting the optimal operating scheme for the fuel cell system.

[0098] In an exemplary embodiment, the above-mentioned generation of offspring population based on parent population further includes: obtaining a first offspring population based on parent population through crossover and mutation operations; calculating the crowding distance of the individual with the highest non-dominant level in parent population; selecting a preset number of individuals from the individuals with the highest non-dominant level in parent population based on the crowding distance, and integrating them into a second offspring population; and combining the first offspring population and the second offspring population into a single offspring population.

[0099] Crowding distance is used to measure the sparsity of the distribution of individuals in the solution space of a population.

[0100] For example, the terminal first performs a crossover operation on individuals in the parent population, generating new individuals by combining the genetic information of two parent individuals. The new individuals inherit some genetic information from their parents but possess new gene combinations, increasing population diversity. Next, the terminal performs a mutation operation, randomly mutating a small number of individuals to introduce new solution spaces and prevent the population from getting trapped in local optima. After the crossover and mutation operations, a first generation population is generated, which inherits the advantageous characteristics of its parents while preserving solution diversity. To ensure population diversity and uniform solution distribution, the terminal calculates the crowding distance of the highest-ranking non-dominated individual in the parent population. Crowding distance measures the sparsity of the distribution of individuals on the Pareto front. Individuals with large crowding distances indicate that the solutions around them are relatively sparse, meaning that these individuals represent more diverse solutions, helping the genetic algorithm search in a wider solution space. Based on the calculated crowding distances, the terminal selects a predetermined number of individuals from the highest-ranking non-dominated individuals in the parent population. During the selection process, individuals with larger crowding distances are prioritized because their solution space is sparser, increasing population diversity and preventing premature convergence to local optima. These selected individuals will form the second generation population. Finally, the terminal oscillation integrates the first generation population generated through crossover and mutation operations with the second generation population selected based on crowding distance, forming the final generation population. This integrated population includes both newly generated individuals from genetic operations and retains the diversity of parent individuals, thus balancing the exploratory and convergent aspects of the solution.

[0101] In this embodiment, by combining crossover and mutation operations with crowding distance screening, a more diverse and representative offspring population is generated. Crossover and mutation operations ensure the evolution of the population and the generation of new solutions, while crowding distance screening preserves high-quality individuals with even distribution and sparse solution space. This not only improves the diversity of the population but also avoids the algorithm getting trapped in local optima, ultimately making the prediction of fuel cell system operation schemes more accurate and efficient.

[0102] In an exemplary embodiment, step S202, which calculates the fitness of each individual in the current population, further includes: constructing a simulation model of the fuel cell system to be predicted in a physical simulation tool; and calculating the fitness of each individual in the current population based on the simulation model in the physical simulation tool.

[0103] Furthermore, step S203 above, which generates a progeny population based on fitness and the current population, also includes: using an optimization prediction tool to generate a progeny population based on fitness and the current population.

[0104] Physical simulation tools are used to build simulation models of fuel cell systems and calculate the performance of each individual component based on the model, thereby evaluating their fitness. Common physical simulation tools include EES (Engineering Equation Solver), Aspen Plus, COMSOL Multiphysics, and GT-SUITE.

[0105] Among them, optimization prediction tools are used to generate offspring populations based on selection, crossover, and mutation operations of the genetic algorithm after fitness calculation. These tools can be MATLAB (especially MATLAB's Genetic Algorithm Toolbox), Python with DEAP, GAMS (General Algebraic Modeling System), and Genetic Algorithm for Python (GAFT) (a Python library specifically for genetic algorithms that supports solving complex optimization problems), etc.

[0106] For example, the terminal constructs a simulation model of the fuel cell system by calling a physical simulation tool (such as EES). This model includes key elements such as the system's operating parameters, thermodynamic equilibrium, and chemical reactions. By inputting each individual (i.e., parameter combination) in the current population into the simulation model, the physical simulation tool can calculate the performance of each individual and convert it into a fitness value. For example, the simulation tool can evaluate the merits of each individual based on objective functions such as system efficiency and hydrogen utilization rate. The terminal then performs genetic algorithm operations on the current population by calling an optimization prediction tool (such as MATLAB). Based on the fitness value, the terminal prioritizes individuals with higher fitness for genetic operations to generate a new offspring population. Crossover is used to combine the genes of parent individuals to generate offspring individuals with new parameter combinations; mutation introduces randomness to ensure population diversity and prevent the population from getting trapped in local optima.

[0107] In this embodiment, the fitness of each individual is accurately calculated using physical simulation tools, and combined with the genetic algorithm operation of the optimization prediction tool, the terminal can efficiently generate new offspring populations. The combined use of these tools not only ensures the accuracy of the system simulation calculations but also enables rapid iterative optimization, helping the fuel cell system scheme prediction achieve optimal performance and economy.

[0108] In another exemplary embodiment, as shown in FIG3, this application provides a method for predicting the operation scheme of a fuel cell system, the method comprising the following steps:

[0109] Step S301: Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range of the preset operating parameters.

[0110] Step S302: Perform sensitivity analysis on each preset operating parameter item, obtain the analysis results, and determine the preset value accuracy corresponding to each preset operating parameter item based on the analysis results.

[0111] Step S303: Based on the preset value range and preset value precision, randomly generate multiple sets of operating parameter values ​​for the preset operating parameter items.

[0112] Step S304: Determine the encoding length corresponding to the preset running parameter item based on the preset value range and preset value precision.

[0113] Step S305: Determine the encoding relationship of the preset running parameter items according to the encoding length. Based on the encoding relationship, convert each running parameter value into encoding information as the gene information of individuals in the genetic algorithm to obtain the initial population.

[0114] Step S306: Obtain preset constraint information and multiple preset objective functions; based on the preset constraints and each preset objective function, obtain the fitness function of individuals in multiple genetic algorithms.

[0115] Step S307: Take the initial population as the current population and calculate the fitness of each individual in the current population.

[0116] Step S308: Based on fitness, sort the individuals in the current population by non-dominance and determine the non-dominance level of each individual in the current population.

[0117] Each non-dominated level contains at least one individual.

[0118] Step S309: Remove the individual with the lowest non-dominant level from the current population to obtain the parent population. Based on the parent population, obtain the first offspring population through crossover and mutation operations.

[0119] Step S310: Calculate the crowding distance of the individual with the highest non-dominant level in the parent population. Based on the crowding distance, select a preset number of individuals from the individuals with the highest non-dominant level in the parent population and integrate them into the second offspring population.

[0120] Step S311: Combine the first and second offspring populations into a single offspring population, use this offspring population as the new current population, and return to step S307 until an offspring population that meets the preset conditions is obtained.

[0121] Step S312: Determine the predicted operation scheme of the fuel cell system to be predicted based on the offspring population that meets the preset conditions.

[0122] In this embodiment, the selective optimization mechanism of the genetic algorithm can gradually eliminate solutions that do not meet the objective, avoiding indiscriminate calculations for every parameter combination. Compared to the uniform partitioning in traditional methods, and considering the accuracy of each preset operating parameter, the genetic algorithm, through selection, crossover, and mutation during the evolutionary process, gradually reduces attention to secondary parameters and focuses on optimizing key parameters, significantly alleviating unnecessary computational burden. Ultimately, this improves the prediction efficiency of fuel cell system operation schemes and the utilization rate of computing resources, enabling the entire optimization process to maintain accuracy while achieving higher computational efficiency. This not only effectively overcomes the limitations of traditional optimization methods in handling complex, nonlinear, and multi-objective problems, but also significantly improves the design and optimization efficiency of fuel cell systems through intelligent means, providing strong support for technological advancements in the new energy field.

[0123] In an exemplary embodiment, as shown in FIG4, it is a schematic diagram of the fuel cell system to be predicted for performing the fuel cell system operation scheme prediction method.

[0124] Specifically, the fuel cell system consists of three parts: a solid oxide fuel cell system, a transcritical carbon dioxide cycle, and an LNG (liquefied natural gas) cold energy utilization system. The SOFC (Solid Oxide Fuel Cell) system includes a two-stage compression intercooled air compressor (AC1 and AC2), a condenser (HE1), a fuel compressor (FC), a water pump (WP), two air preheaters (PH1 and PH2), a fuel preheater (PH3), a water preheater (PH4), a mixer (M), a turbine (T3), a planar direct internal reforming (DIR) SOFC stack, an AC / DC inverter, an afterburner (AB), and a gas turbine (GT). The transcritical carbon dioxide cycle includes a heat recovery steam generator (HRVG), a carbon dioxide turbine (T2), a regenerator (R), a carbon dioxide pump (P1), and a condenser (Con). The LNG cold energy utilization system consists of an LNG storage tank, an LNG pump (P2), a cold storage (HE2), and a heat exchanger (HE3).

[0125] In fuel cell systems, the net output power of the fuel cell system is one of the important indicators commonly used to evaluate the work capacity of a fuel cell. In this system, it can be expressed as: W SOFC,net =W SOFC +W GT -W c,fuel -W c,air -W pump

[0126] Among them, W GT The power output of the gas turbine in an SOFC system is expressed in kW (W).c,fuel Power consumption of the fuel compressor in an SOFC system, kW; W c,air Power consumption of air compressor (kW); W pump Pump power consumption / kW.

[0127] In the bottom cycle of this system, the transcritical carbon dioxide cycle driven by waste heat provided by the waste heat boiler and the LNG cooling... The systems are connected in series. The output work of the series cycle system represents the amount of waste heat recovered from the main system, which is expressed in this system as:

[0128] Among them, W SOFC,net Net output power of SOFC system, kW; W CO2,net Net power output of the transcritical carbon dioxide cycle, kW; W LNG,net The net output power of the LNG system is expressed in kW.

[0129] Thermal efficiency of TRCC (Transcritical CO2 Cycle) combined bottom cycle system with LNG:

[0130] Where h is the enthalpy, a physical quantity; m is the mass flow rate; h 19 This represents the enthalpy value of node 19 in Figure 4, h. 24 This represents the enthalpy value of node 24 in Figure 4; m CO2 This represents the mass flow rate of carbon dioxide. The thermal efficiency of an SOFC system is expressed as:

[0131] Among them, Q SOFC It is the input energy of fuel in a fuel cell system.

[0132] The overall thermal efficiency of the system is:

[0133] In this system, the economic feasibility evaluation criteria are based on the following three points: product operation and maintenance costs, internal rate of return, and discounted payback period. The input parameters for the economic analysis are shown in Tables 1, 2, and 3, where the total cost rate is expressed in US dollars per second.

[0134] Table 1 Input Parameters for Economic Analysis

[0135] Table 2 Input Parameters for Economic Analysis

[0136] Table 3 Input Parameters for Economic Analysis

[0137] The definitions of each parameter in the above economic analysis input parameter table are shown in Table 4 below.

[0138] Table 4 Parameter Explanation Table

[0139] Based on the parameters listed in the table above, assess the capital costs of the SOFC / GT, TRCC, and liquefied natural gas subsystems. The unit-time cost rate for each investment project is calculated as follows:

[0140] Among them, Z k CRF, N, and CRF represent the cost of capital, capital recovery factor, maintenance factor, and annual operating time, respectively. CRF is the ratio of a fixed annuity to the present value of the annuity received over the investment period, calculated as follows:

[0141] Where i and n are the interest rate and system lifetime, respectively.

[0142] In addition to the fixed costs of the components mentioned above, the system cost also needs to include the system's fuel cost. The fuel cost rate is assessed based on the unit cost of natural gas and is defined as follows:

[0143] Where, m f This refers to the mass of fuel.

[0144] The optimization objective of the above system is to achieve a higher overall thermal efficiency (TFE) of the fuel cell cogeneration system. The goal is to maximize efficiency while minimizing the total system cost. Higher cell counts, higher cell input temperatures, and lower circuit density in a fuel cell stack generally lead to higher system efficiency, but also higher system costs—a seemingly contradictory relationship. Furthermore, these two factors are independent and have low correlation, meeting the selection criteria for the objective function in multi-objective optimization.

[0145] The main constraint of the above system is the temperature difference between each heat exchanger. It requires that the temperature difference at each port of each heat exchanger be correct and meet the temperature conditions of the hot and cold ends.

[0146] For example, a comprehensive evaluation model of fuel cell system performance parameters and economic indicators was first constructed, clarifying the specific quantitative indicators and weight allocation of each objective. Subsequently, sensitivity analysis was used to identify key parameters that significantly affect system performance and economy, such as fuel utilization rate, current density, and catalyst activity, and a sensitivity matrix for these parameters was constructed to provide a scientific basis for subsequent optimization. Based on this, this invention innovatively applies a genetic algorithm to the multi-objective optimization of fuel cell systems. Through an encoding mechanism, the value ranges of each key parameter are transformed into a chromosome structure in the genetic algorithm, with each chromosome representing a set of potential optimization schemes. The algorithm uses a fitness function to evaluate the comprehensive performance and economy of different chromosomes (i.e., different parameter combinations), which comprehensively considers the improvement in system performance parameters and the economic cost required to achieve these improvements. During the iterative process of the genetic algorithm, selection operations retain superior individuals, crossover operations integrate the advantages of different superior individuals, and mutation operations introduce new gene combinations, continuously generating and screening better chromosomes (parameter combinations). In this process, based on the results of sensitivity analysis, a more refined encoding and search strategy is adopted for highly sensitive parameters to ensure the accuracy of their optimization; while for low-sensitivity parameters, the search range is appropriately broadened to improve optimization efficiency. As the number of iterations increases, the algorithm gradually approaches the global optimum, ultimately obtaining one or more optimization schemes that can significantly improve the performance parameters of the fuel cell system while effectively controlling economic costs. The optimization method of this invention not only effectively overcomes the limitations of traditional optimization methods in handling complex, nonlinear, and multi-objective problems, but also significantly improves the design and optimization efficiency of fuel cell systems through intelligent means, providing strong support for technological advancements in the new energy field.

[0147] In practical applications, the system simulation process is run in the commercial software EES, relying on EES's comprehensive gas thermophysical property parameter database. However, in the subsequent multi-objective optimization process, EES cannot meet the system's optimization requirements. Therefore, a multi-software collaborative simulation approach is proposed: combining the MATLAB genetic algorithm toolbox with EES. The state parameters of each point in the system are calculated using the EES property parameter database, generating a matrix document. The MATLAB program then calls the optimization toolbox to read the state parameters of each point. The genetic algorithm calculates the input parameters for the next generation of the system and feeds them back to EES to continue calculating the state of each point, thus forming a collaborative simulation closed loop. As shown in Figure 5, the final optimized data is obtained through repeated parameter calls and iterative calculations.

[0148] This embodiment not only focuses on optimizing the performance parameters of the fuel cell system, but also delves into and balances various performance indicators such as efficiency, power density, and durability through a highly efficient global search technique called genetic algorithm. Furthermore, it incorporates economic analysis as a core consideration, including cost-effectiveness, operating and maintenance costs, and investment payback period. By constructing a multi-objective optimization model, we strive to effectively control and optimize the economic costs while improving system performance. Simultaneously, a multi-software collaborative computation mechanism is established to form a unified optimization method, optimize the calculation process, and improve computational efficiency.

[0149] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0150] Based on the same inventive concept, this application also provides a fuel cell system operation plan prediction device for implementing the above-described fuel cell system operation plan prediction method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the fuel cell system operation plan prediction device provided below can be found in the limitations of the fuel cell system operation plan prediction method described above, and will not be repeated here.

[0151] In an exemplary embodiment, as shown in FIG6, a fuel cell system operation scheme prediction device is provided, comprising: an information acquisition module 601, a parameter generation module 602, a gene conversion module 603, and a scheme prediction module 604, wherein:

[0152] The information acquisition module 601 is used to acquire the preset operating parameters of the fuel cell system to be predicted, as well as the preset value range and preset value accuracy of the preset operating parameters.

[0153] The parameter generation module 602 is used to randomly generate multiple sets of operating parameter values ​​for preset operating parameter items according to the preset value range and preset value precision;

[0154] The gene conversion module 603 is used to convert each running parameter value into the gene information of an individual in the genetic algorithm to obtain the initial population;

[0155] The scheme prediction module 604 is used to obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

[0156] In one embodiment, the gene conversion module 603 is further configured to determine the encoding length corresponding to the preset running parameter item based on the preset value range and preset value precision; determine the encoding relationship of the preset running parameter item based on the encoding length; and convert each running parameter value into encoding information based on the encoding relationship, which serves as the gene information of an individual in the genetic algorithm.

[0157] In one embodiment, the above-mentioned scheme prediction module 604 is further configured to obtain the fitness function of individuals in multiple genetic algorithms according to preset constraints and preset objective functions; take the initial population as the current population and calculate the fitness of each individual in the current population; generate a progeny population according to the fitness and the current population, take the progeny population as the new current population, and return to execute the step of calculating the fitness of each individual in the current population until a progeny population that meets the preset conditions is obtained; and determine the predicted operation scheme of the fuel cell system to be predicted according to the progeny population that meets the preset conditions.

[0158] In one embodiment, the above-mentioned scheme prediction module 604 is further configured to perform non-dominated sorting of individuals in the current population according to fitness, determine the non-dominated level of each individual in the current population; each non-dominated level contains at least one individual; remove the individual with the lowest non-dominated level from the current population to obtain the parent population; and generate the offspring population based on the parent population.

[0159] In one embodiment, the above-mentioned scheme prediction module 604 is further configured to obtain a first offspring population based on the parent population through crossover and mutation operations; calculate the crowding distance of the individual with the highest non-dominant level in the parent population; select a preset number of individuals from the individuals with the highest non-dominant level in the parent population based on the crowding distance, and integrate them into a second offspring population; and combine the first offspring population and the second offspring population into a single offspring population.

[0160] In one embodiment, the above-mentioned scheme prediction module 604 is further configured to construct a simulation model of the fuel cell system to be predicted in a physical simulation tool; calculate the fitness of each individual in the current population based on the simulation model in the physical simulation tool; and generate a offspring population based on the fitness and the current population using an optimization prediction tool.

[0161] The modules in the aforementioned fuel cell system operation prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0162] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram is shown in Figure 7. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for predicting the operation scheme of a fuel cell system. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0163] Those skilled in the art will understand that the structure shown in Figure 7 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0164] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0165] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0166] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0169] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0170] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting the operation scheme of a fuel cell system, characterized in that, The method includes: Obtain the preset operating parameters of the fuel cell system to be predicted, and obtain the preset value range and preset value precision of the preset operating parameters; Based on the preset value range and preset value precision, multiple sets of operating parameter values ​​for the preset operating parameter items are randomly generated; Each of the aforementioned operating parameter values ​​is converted into the genetic information of an individual in the genetic algorithm to obtain the initial population; Obtain preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each preset objective function and the initial population.

2. The method according to claim 1, characterized in that, The step of converting each of the aforementioned operating parameter values ​​into the genetic information of an individual in the genetic algorithm includes: The encoding length corresponding to the preset running parameter item is determined based on the preset value range and preset value precision; Based on the encoding length, determine the encoding relationship of the preset running parameter items; Based on the encoding relationship, each of the running parameter values ​​is converted into encoded information, which serves as the genetic information of an individual in the genetic algorithm.

3. The method according to claim 1, characterized in that, The step of obtaining the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each of the preset objective functions, and the initial population includes: Based on the preset constraints and the preset objective functions, the fitness functions of individuals in multiple genetic algorithms are obtained; Using the initial population as the current population, calculate the fitness of each individual in the current population; Based on the fitness and the current population, a offspring population is generated, and the offspring population is used as the new current population. The process of calculating the fitness of each individual in the current population is then repeated until an offspring population that meets the preset conditions is obtained. Based on the offspring population that meets the preset conditions, a predictive operation scheme for the fuel cell system to be predicted is determined.

4. The method according to claim 3, characterized in that, The step of generating a offspring population based on the fitness and the current population includes: Based on the fitness, individuals in the current population are sorted by non-dominance to determine the non-dominance level of each individual in the current population; each non-dominance level contains at least one individual. From the current population, remove the individual with the lowest non-dominant level to obtain the parent population; The offspring population is generated based on the parent population.

5. The method according to claim 4, characterized in that, The step of generating a child population based on the parent population includes: Based on the parent population, the first offspring population is obtained through crossover and mutation operations; Calculate the crowding distance of the individual with the highest non-dominant level in the parent population; Based on the crowding distance, a predetermined number of individuals are selected from the individuals with the highest non-dominant level in the parent population and integrated into the second offspring population. The first and second offspring populations together constitute the offspring population.

6. The method according to claim 3, characterized in that, The calculation of the fitness of each individual in the current population includes: In a physical simulation tool, a simulation model of the fuel cell system to be predicted is constructed; In the physical simulation tool, the fitness of each individual in the current population is calculated based on the simulation model; The step of generating a offspring population based on the fitness and the current population includes: An optimized prediction tool is used to generate a offspring population based on the fitness and the current population.

7. A device for predicting the operation scheme of a fuel cell system, characterized in that, The device includes: The information acquisition module is used to acquire preset operating parameters of the fuel cell system to be predicted, as well as the preset value range and preset value precision of the preset operating parameters. The parameter generation module is used to randomly generate multiple sets of operating parameter values ​​for the preset operating parameter items based on the preset value range and preset value precision. The gene conversion module is used to convert each of the above-mentioned running parameter values ​​into the gene information of individuals in the genetic algorithm to obtain the initial population; The scheme prediction module is used to acquire preset constraint information and multiple preset objective functions, and obtain the predicted operation scheme of the fuel cell system to be predicted based on the preset constraints, each of the preset objective functions and the initial population.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. 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 6.

10. A computer program product, comprising a computer program, 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 6.

Images