Zero-carbon power system modeling method and system based on closed-loop feedback optimized order reduction

Abstract

The present invention discloses a zero-carbon power system modeling method and system based on closed-loop feedback optimization and order reduction, which relates to the field of zero-carbon power system modeling and combustion mechanism optimization. The chemical reaction mechanism network of the zero-carbon power system is reduced in mechanism to obtain the key reaction path; an improved dynamic force model is used to perform dynamic layout on the energy network constructed based on the key reaction path to obtain a dynamic energy network; a closed-loop feedback mechanism is used to optimize the dynamic energy network to obtain a simplified mechanism network; multi-dimensional data of the simplified mechanism network is obtained and feature extraction is performed to obtain a low-dimensional feature vector; the low-dimensional feature vector is input into a comprehensive mapping model for prediction to obtain the prediction result of the key combustion parameters. The method of using a directed relationship graph with plasma and error propagation in combination with a closed-loop feedback mechanism to reduce the order of the mechanism network, reduce the dimension of its multi-dimensional data, and utilize a multi-model fusion strategy to achieve high-precision and fast-response prediction of key combustion parameters.

Description

Technical Field

[0001] The present invention relates to the field of zero-carbon power system modeling and combustion mechanism optimization, and particularly to a zero-carbon power system modeling method and system based on closed-loop feedback optimization and model reduction. Background Art

[0002] The statements in this section merely provide background technical information related to the present disclosure and do not necessarily constitute prior art.

[0003] With the increasing global demand for clean energy and efficient combustion technologies, zero-carbon power systems have become an important direction for future energy transformation. With the global high emphasis on zero carbon emissions and sustainable energy, zero-carbon power systems have become a key direction for energy technology innovation. Traditional combustion technologies are gradually difficult to meet the requirements of the new generation of clean energy systems in terms of energy efficiency, emission control, and system safety. Therefore, high-precision modeling and real-time optimization methods based on digital technologies have received extensive attention. Digital zero-carbon power systems can not only achieve efficient energy conversion but also ensure the stable and safe operation of the system under complex working conditions by integrating high-precision modeling, real-time monitoring, and intelligent optimization.

[0004] In recent years, plasma-assisted combustion technology has received attention because it can stimulate combustion reactions at low temperatures, accelerate fuel decomposition, and expand the fuel flammability limit. However, it also brings complex non-linear and multi-scale coupling problems. Traditional combustion mechanisms mostly rely on thermochemical reaction descriptions and are difficult to effectively solve the high computational complexity and time-scale stiffness problems caused by microscopic processes such as electron collision, excitation, and ionization during plasma discharge. These challenges not only limit the possibility of real-time simulation and optimization of the combustion process but also pose higher requirements for the digital modeling and control of zero-carbon power systems.

[0005] Currently, researchers have tried to simplify the mechanism of complex reaction networks using global path analysis, zero-dimensional solvers, and data-driven dimensionality reduction methods. However, most methods still have problems such as limited applicability, difficulty in balancing computational accuracy and response speed, and are difficult to meet the requirements of high-precision and fast response of the combustion process in future zero-carbon power systems under multi-fuel and multi-working-condition conditions. For example, many simplification methods ignore the multi-scale coupling effects occurring in complex combustion processes, especially the interaction between plasma and fuel systems. Due to the strong non-linear characteristics of processes such as electron collision, excitation, and ionization in plasma, traditional methods usually cannot provide sufficient real-time response and accuracy when dealing with these microscopic processes. Summary of the Invention

[0006] To overcome the deficiencies of the above-mentioned existing technologies and address the problems of complex plasma-assisted combustion reaction mechanism networks, low multi-scale coupling calculation efficiency, and insufficient real-time control accuracy in zero-carbon power systems, the present invention provides a zero-carbon power system modeling method and system based on closed-loop feedback optimization and order reduction. By reducing the dimension of the reaction mechanism network and input data while retaining key physical and chemical processes, and using a multi-model fusion strategy to capture the non-linear mapping between key variables and predicted outputs, the efficiency and accuracy of numerical simulations are significantly improved.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0008] In a first aspect, the present invention provides a zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction, including:

[0009] Obtain the chemical reaction mechanism network of the zero-carbon power system and its multi-dimensional data;

[0010] Perform mechanism order reduction on the chemical reaction mechanism network based on the multi-dimensional data to obtain key reaction paths;

[0011] Construct an energy network based on the key reaction paths, perform dynamic layout on the energy network using an improved dynamic force model to obtain a dynamic energy network; optimize the dynamic energy network using a closed-loop feedback mechanism to obtain a simplified mechanism network;

[0012] Obtain the multi-dimensional data of the simplified mechanism network and perform preprocessing, and perform principal component analysis on the preprocessed multi-dimensional data to obtain low-dimensional feature vectors;

[0013] Input the low-dimensional feature vectors into a pre-trained comprehensive mapping model for prediction to obtain the prediction results of key combustion parameters.

[0014] In a further technical solution, the mechanism order reduction of the chemical reaction mechanism network is performed using a directed relationship graph method with plasma error propagation, and the direct interaction coefficients between species and various energy branch variables are calculated. When the direct interaction coefficient is less than a set error threshold, the corresponding species and their related redundant reactions are removed to obtain a skeletal mechanism.

[0015] In a further technical solution, first use depth-first search to traverse the skeletal mechanism to automatically identify key reaction paths, and then perform a review of the retained reaction paths in combination with reaction path analysis.

[0016] In a further technical solution, constructing an energy network based on key reaction paths specifically means: constructing a visualization network based on key reaction paths, and stratifying different species in the visualization network based on the energy types of the species to obtain an energy network.

[0017] A further technical solution is to introduce an energy-sensitive force mechanism into the ForceAtlas2 model to obtain an improved dynamic force model, including a repulsive force model, an attractive force model, and a random perturbation term.

[0018] A further technical solution is that the closed-loop feedback mechanism is specifically as follows:

[0019] Use the improved dynamic force model to perform spatial layout on the energy network, visually sort the species nodes according to the reaction intensity and influence, and obtain the node importance ranking;

[0020] Calibrate the high-importance nodes based on the node importance ranking, and calculate the average distance between each pair according to the spatial coordinates of the high-importance nodes;

[0021] Based on the average distance, use a feedback adjustment strategy to adjust the error threshold in the directed graph method with plasma band error propagation, and perform mechanism order reduction based on the adjusted error threshold;

[0022] Iterate the above steps. When the error thresholds of all species nodes meet the convergence conditions, stop the closed-loop and output the simplified mechanism network.

[0023] A further technical solution is to form a comprehensive mapping model based on a multi-model fusion prediction framework, specifically as follows:

[0024] Construct a candidate model library containing multiple candidate models;

[0025] Adopt all candidate models The method of k-fold cross-validation is used for training and performance evaluation, and the fusion weights of each candidate model are obtained based on the performance evaluation;

[0026] Construct a comprehensive mapping model based on each candidate model and the corresponding fusion weights.

[0027] In a second aspect, the present invention provides a zero-carbon power system modeling system based on closed-loop feedback optimization and order reduction, including:

[0028] A data acquisition module, which is configured to: acquire the chemical reaction mechanism network and its multi-dimensional data of the zero-carbon power system;

[0029] A mechanism order reduction module, which is configured to: perform mechanism order reduction on the chemical reaction mechanism network based on the multi-dimensional data to obtain the key reaction path;

[0030] A closed-loop feedback optimization module, which is configured to: construct an energy network based on the key reaction path, use the improved dynamic force model to perform dynamic layout on the energy network to obtain a dynamic energy network; use a closed-loop feedback mechanism to optimize the dynamic energy network to obtain a simplified mechanism network;

[0031] A feature extraction module, which is configured to: obtain multi-dimensional data based on the reduced mechanism network and perform preprocessing, and perform principal component analysis on the preprocessed multi-dimensional data to obtain a low-dimensional feature vector;

[0032] A model prediction module, which is configured to: input the low-dimensional feature vector into a pre-trained comprehensive mapping model for prediction to obtain a prediction result of key combustion parameters.

[0033] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction described in the first aspect are implemented.

[0034] In a fourth aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps in the zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction described in the first aspect are implemented.

[0035] The above one or more technical solutions have the following beneficial effects:

[0036] The present invention uses the plasma band error propagation directed relationship graph method P-DRGEP, the depth-first search method DFS, and the reaction path analysis RPA to perform preliminary mechanism reduction on the original chemical reaction mechanism network to obtain key reaction paths, and then uses an improved dynamic force model to realize the real-time visualization of the mechanism network. According to the visualization analysis of the mechanism network and combined with the closed-loop feedback mechanism, further optimization and reduction of the key reaction paths are carried out to obtain the final reduced mechanism network, realizing the real-time optimization of the mechanism network and significantly improving the reliability of the mechanism simplification process.

[0037] The present invention reduces the dimension of multi-dimensional data through principal component analysis, extracts low-dimensional feature vectors, and combines with a multi-model fusion prediction framework for prediction, breaking through the limitations of a single model and improving the prediction accuracy of key combustion parameters.

[0038] The present invention innovatively proposes a closed-loop feedback mechanism, which forms an intelligent closed loop through the dynamic adjustment of the visualization layout and error threshold to ensure the reliability and energy conservation of the mechanism network simplification.

[0039] The present invention uses mechanism reduction and data-driven multi-model integrated prediction to efficiently model and simulate and optimize complex chemical reaction processes. During the mechanism reduction process, key physical and chemical processes are retained to ensure accurate characterization of reaction kinetics and energy balance. At the same time, relying on advanced multi-model fusion prediction technology, traditional regression methods and modern machine learning algorithms are integrated to achieve high-precision and fast-response prediction of key combustion parameters (such as temperature, concentration of main species, etc.) of the zero-carbon power system, so as to meet the strict requirements for system safety, energy efficiency and emission control under actual working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings forming a part of this invention are used to provide a further understanding of the invention. The schematic embodiments and descriptions thereof of the invention are used to explain the invention and do not constitute an improper limitation of the invention.

[0041] Figure 1 is a flowchart of the zero-carbon power system modeling method based on closed-loop feedback optimization reduction according to an embodiment of the present invention;

[0042] Figure 2 is a flowchart of visual intelligent reaction mechanism simplification according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0044] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0045] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0046] Embodiment 1

[0047] As Figure 1 shown, this embodiment discloses a zero-carbon power system modeling method based on closed-loop feedback optimization reduction, and the method includes the following steps:

[0048] S1: Obtain the chemical reaction mechanism network and its multi-dimensional data of the zero-carbon power system;

[0049] In this embodiment, for the zero-carbon power system (such as For the research on plasma-assisted combustion in an air-fuel system, it is necessary to first construct a complete chemical reaction mechanism network. This mechanism is based on the reaction data disclosed in existing literature and combines the plasma-fuel interaction process concerned in the present invention. Through screening, integration, and format conversion, it forms an input format suitable for solvers such as ZDPlasKin / ChemKin. The chemical reaction mechanism network includes key reaction paths such as electron collision, excitation, ionization, radical generation, fuel oxidation, and consumption of intermediate species.

[0050] Among them, the reaction rate constant of each reaction is expressed by the Arrhenius formula:

[0051]

[0052] Among them, represents the pre-exponential factor, represents the temperature, represents the temperature exponent, represents the activation energy, represents the gas constant.

[0053] The chemical reaction mechanism network details the generation, transformation, and consumption processes of each reaction path and intermediate products. To ensure the completeness of the mechanism data, it is necessary to collect multi-dimensional data such as temperature, pressure, species concentration, and reaction rate at the same time, and preliminarily organize the collected multi-dimensional data (numerical simulation data) to provide basic support for subsequent data analysis.

[0054] S2: Based on the multi-dimensional data, perform mechanism reduction on the chemical reaction mechanism network to obtain the key reaction path;

[0055] In this embodiment, since the complete mechanism contains a large number of reactions and species, directly solving it often faces problems such as high computational complexity and difficulty in meeting real-time simulation. Therefore, the directed relationship graph method with error propagation in plasma (P-DRGEP), depth-first search method, and reaction path analysis method are used to reduce the order of the mechanism network.

[0056] Directed relationship graph method with error propagation in plasma (P-DRGEP):

[0057] The DRG (Directed Reduced Graph) algorithm defines the normalized contribution of species to the generation amount of species , so as to quantify the dependence of species on species . If is very large, it means that removing species from the detailed mechanism will cause the generation of species The prediction has a large error. Set an appropriate threshold. If is less than this threshold, it is considered that the species for the species the normalized contribution to the production rate is very small, and the species and its related redundant reactions can be removed. If is greater than this threshold, the species is retained. By continuously adjusting the threshold, a skeletal mechanism with gradually fewer species and reactions is obtained.

[0058] is defined as follows:

[0059]

[0060] where represents the th reaction in the reaction sequence, represents the elementary reaction series, represents the th reaction, the net chemical reaction stoichiometric coefficient of the species , represents the th reaction net chemical reaction rate; when and are both involved in the th reaction, is 1, otherwise it is 0.

[0061] Error propagation is introduced in the DRG algorithm to obtain the directed relationship graph method based on error propagation (DRGEP), and the definition is specifically shown as the following formula:

[0062]

[0063]

[0064]

[0065] where represents the direct interaction relationship between the species and the species , represents the reaction, represents the total production rate of the species, which is non - negative; represents the total digestion rate of the species, which is non - negative.

[0066] The Plasma-targeted Directed Relation Graph with Error Propagation (P-DRGEP) method is obtained by introducing the direct interaction of energy branches and strict error propagation analysis on the basis of the traditional DRGEP. During the plasma-assisted combustion process, electrons lose energy in collision reactions such as ionization, electron excitation, vibrational excitation, and dissociation. These processes constitute the "energy branches", and their characteristics are different from those of a single chemical species in the traditional mechanism.

[0067] species with the th energy branch variable, the direct interaction coefficient is expressed as , and the formula is expressed as:

[0068]

[0069]

[0070] where includes ionization, electron excitation, vibrational excitation, and dissociation, represents the total energy-related quantity of the th energy branch (such as ionization, electron excitation, etc.), represents the reaction set related to the th energy branch, represents the energy corresponding to the th reaction, which is the basic unit constituting ; is the ionization or excitation energy, represents Avogadro's constant, represents the th net chemical reaction rate of the reaction.

[0071] The P-DRGEP method dynamically adjusts the error threshold through a closed-loop feedback mechanism to ensure that key reactions and species are retained in the simplified mechanism network, achieving an accurate match with the original mechanism network in terms of reaction dynamics and energy flow. Specifically, similar to the screening principle of the DRG algorithm, a suitable error threshold is set. If is less than the set error threshold, it is considered that the species has a very small regularized contribution to the generation rate of a certain species of the type, and the species and its related redundant reactions can be removed. If it is greater than the threshold, the species is retained. By continuously adjusting the error threshold, a skeletal mechanism with gradually decreasing numbers of species and reactions is obtained.

[0072] The depth - first search method (DFS) is an important graph search algorithm that traverses the nodes in a graph in a depth - first manner. Regarding the chemical reaction mechanism network as a graph structure, where the nodes represent reactants, intermediates, and products, and the edges represent individual chemical reactions, with kinetic parameters such as reaction rates, initial concentrations of each species, temperature, etc. attached to the edges, data attributes of each node and edge in the graph are constructed. Starting from the main reactant, all possible reaction paths are recursively traversed in a DFS manner.

[0073] Furthermore, starting from important starting species in the zero - carbon power system (such as or plasma - induced electronically excited states) as the search starting point, for each reaction path, calculate its reaction flux or contribution index (such as the contribution of a certain reaction path to the formation of the final product under specific operating conditions). During the search process, use time - step data, reaction rate constants, and transient species concentrations to evaluate the "weight" or importance of each reaction branch. Set a threshold for reaction flux or contribution. If the contribution of a certain branch (i.e., a series of consecutive reactions) in the overall reaction system is lower than the set threshold, it is considered that its impact on the system response is weak. Record these branches during the DFS traversal process and remove them in subsequent steps to ensure the continuity of the core reaction chain is not disrupted (such as the cyclic paths in the reaction mechanism).

[0074] Specifically, as Figure 2 shown, first use depth - first search (DFS) to traverse the entire skeletal mechanism, automatically identify the key reaction paths containing characteristic species (such as cyclic reaction paths ); then, combined with reaction path analysis (RPA), review the retained reaction paths, calculate the element transfer flux and energy absorption and release heat contributions in each path chain, so as to determine the impact of each step of the reaction on rapid heating and the overall energy balance.

[0075] Furthermore, process the skeletal mechanism using the RPA reaction path analysis method. For the retained plasma species, based on the net chemical reaction rate and chemical reaction stoichiometric coefficients of the reaction, obtain the quantitative contribution of each path to the generation and consumption of this species, and remove the reaction paths with a contribution of 0. And based on the DFS traversal search results, ensure that the reaction paths involving the core reaction chain are not removed.

[0076] S3: Construct an energy network based on the key reaction paths, perform dynamic layout on the energy network using an improved dynamic force model to obtain a dynamic energy network; use a closed - loop feedback mechanism to optimize the dynamic energy network to obtain a simplified mechanism network;

[0077] The present invention is directed to zero - carbon power systems (such as / The complex energy flow characteristics of the air-fuel system plasma-assisted combustion) To further improve the dynamic response and visualization level of mechanism simplification, an innovative mechanism integrating dynamic visualization analysis and intelligent feedback is proposed. By deeply coupling the plasma energy transfer characteristics, reaction kinetic data, and improved dynamic force model, real-time mapping of energy contributions and closed-loop optimization of mechanism reduction are achieved.

[0078] In this embodiment, during the plasma-assisted combustion process, multiple dynamic reaction paths and the emergence and disappearance of species are involved. Therefore, constructing a dynamic energy network is the core of real-time analysis and mechanism simplification. The construction of this network is based on the following points: Closed-loop screening is based on the distribution obtained by visualization, adjusting the error threshold of the P-DRGEP method. Species are used as nodes in the visualization layout. For each species: if the propagation error is small and the layout distance is large, the error threshold is reduced; otherwise, the error threshold is increased. All are constructed based on the data (multi-dimensional data) obtained from numerical simulations after preliminary reduction.

[0079] As Figure 2 shown, S301: Construct a visualization network based on the key reaction path, and stratify different species in the visualization network based on the energy type of the species to obtain an energy network.

[0080] Construct a visualization network containing plasma active species (electrons , ions , excited state particles , etc.) and key combustion species ( , , ). The attributes of each node include not only the species concentration but also its corresponding energy state (such as ionization energy, excitation energy, etc.). The edges of the visualization network represent the reaction coupling relationships between species, and the weights of the edges are determined by the reaction rate constant or the energy exchange intensity between species.

[0081] To capture the change of species concentration over time, time-slice data is obtained by time-slicing the numerical simulation data of the reduced chemical reaction mechanism network based on the pulse period. By extracting the species concentration, energy contribution, etc. at each moment in each time slice, detailed time-series data can be obtained. The time-series data is the data of the change of species concentration over time, and each time slice is combined into detailed time-series data.

[0082] By performing linear interpolation on the time-slice data, an animation showing the variation of species concentration over time can be generated, visually demonstrating the emergence and disappearance of species. This process provides an important reference for analyzing the dynamic behavior of species during plasma discharge. Based on the energy types of species (such as ionization, excitation, etc.), different species are stratified in the generated visualization network, and species with different energy levels are distributed on the Z-axis to obtain an energy network. That is to say, through linear interpolation, the segmented time steps are made consistent, and the animation is generated by visualizing each time step and then dynamically displaying it. The plasma species are classified so that species with different energy levels are distributed differently, making the visualization clearer.

[0083] S302: Use an improved dynamic force model to perform dynamic layout on the energy network, enabling the distribution of the energy network in two-dimensional or three-dimensional space to reflect the emergence and disappearance of species during the combustion process in real time, and obtaining a dynamic energy network.

[0084] Regarding the energy flow characteristics of plasma-assisted combustion, an energy-sensitive force mechanism is introduced into the classical ForceAtlas2 model to obtain an improved dynamic force model. It specifically includes the following three sub-modules:

[0085] The energy network has been constructed previously, including node-edge weights. The repulsive force, gravitational force, and random perturbation defined below determine the distance distribution of these nodes in the energy network.

[0086] Repulsive force model: To highlight the core nodes of the energy network, the repulsive force between nodes is inversely proportional to the P-DRGEP error propagation value (or uncertainty propagation coefficient), and the error propagation value is defined as follows:

[0087]

[0088] Among them, represents the error propagation value, represents the species and the direct interaction coefficient between the

[0089] The repulsive force between nodes is defined as follows:

[0090]

[0091] Among them, represents the repulsive force between nodes; represents the repulsive force constant; represents the minimum value, to avoid the denominator being zero; represents the distance between nodes. The above definition can ensure that species with high importance are automatically separated in the layout, forming a core node cluster.

[0092] Gravitational model: The gravity generated by the strong reaction path (i.e., the path with a high reaction rate) will pull the relevant nodes closer, causing them to gather in the energy network. Therefore, the reaction path gravity is positively correlated with the net reaction rate, that is:

[0093]

[0094] where represents the reaction path gravity, represents the gravitational constant. The strong reaction path pulls the nodes closer through gravity to form a tight functional module.

[0095] Random perturbation term: To simulate the network layout fluctuations caused by parameter uncertainties, a random perturbation term is added and defined as:

[0096]

[0097] where represents the random perturbation term, represents the perturbation coefficient, represents a normal distribution random variable with a mean of 0 and a standard deviation of .

[0098] S303: The dynamic energy network is optimized using a closed-loop feedback mechanism to obtain a simplified mechanism network.

[0099] The intelligent feedback is realized through a three-step cyclic iteration between the visualization results (the energy network after dynamic layout) and the mechanism reduction, forming a closed loop of "layout analysis - strategy adjustment - iterative optimization". The specific process is as follows:

[0100] Layout analysis: The improved dynamic force model is used to perform the spatial layout of the energy network. The species nodes are visually sorted according to the reaction intensity and influence to obtain the node importance ranking. The high-importance nodes are marked with a golden border to assist in identifying the dominant reaction chain; the redundant reaction paths are marked with a dotted line to indicate the candidate for elimination; the network edge weight is defined by the direct interaction coefficient or the error propagation coefficient calculated by P-DRGEP, which is used to calibrate the importance of the reaction path.

[0101] Furthermore, the method for judging high-importance nodes: Calculate the rate weighted sum of the nodes in all participating reactions to obtain the rate contribution. Set an importance threshold (such as the top 20%) to calibrate the high-importance nodes, and calculate the average distance between each pair according to the spatial coordinates of the high-importance nodes.

[0102] Furthermore, the redundant reaction path judgment method: edge weight screening (dashed lines are used to mark those below the threshold) and the existence of alternative paths, that is, there are multiple parallel paths between two nodes, and the weight of one of the paths is significantly lower than that of other paths, then this path can be regarded as redundant and can be represented by a dashed line, making the visualization clearer.

[0103] Adopt a feedback adjustment strategy for strategy adjustment: for each target species, calculate the average distance between it and the nearest several (such as 5) neighbor nodes with the strongest direct interaction in the current layout. Record the benchmark value (initial average distance) of these average distances in the first round of iteration, and use this benchmark value as a reference in the subsequent iterations. When in a certain iteration, the average distance of a certain species exceeds 120% of the "benchmark distance", it can be considered that this species is "too loose" in the layout, and then mark this species as "loose"; if the average distance is less than 80% of the "benchmark distance", it is considered that this species is "too aggregated (too close in distance)", and then mark this species as "too aggregated".

[0104] In each iteration, for the species marked as "loose", the error threshold in the P-DRGEP method should be reduced by 5%; for the species marked as "too aggregated", the error threshold should be increased by 5%. If a species belongs to neither "loose" nor "too aggregated", its error threshold can be kept unchanged or slightly retreated (±2%) to avoid long-term stagnation. After updating the single-species threshold, evaluate the average contribution of the four major channels of ionization, electron excitation, vibrational excitation, and molecular dissociation in this round. If the overall contribution is too high (indicating that the threshold is too low and too many paths are retained), then the error thresholds of these four channels are simultaneously increased by 5%; if the overall contribution is too low (excessive elimination), then they are simultaneously decreased by 5%. And set the lower limit to 20% of the median of all direct interaction coefficients of this species and the upper limit to 200% of the median to prevent the error threshold from being adjusted too low resulting in network distortion or too high to eliminate key reactions.

[0105] Iterative optimization: The convergence is determined when the average distance of a certain species is within the range of "80% - 120% of the benchmark" and its error threshold has not changed by more than 2% in three consecutive iterations. It can be considered that the threshold of this species has converged and it will no longer participate in subsequent adjustments. When all target species and the four major channels meet the above convergence conditions, the entire closed-loop can be stopped and the final skeletal mechanism (simplified mechanism network) can be output.

[0106] S4: Obtain the multi-dimensional data of the simplified mechanism network and perform preprocessing on it, and perform principal component analysis on the preprocessed multi-dimensional data to obtain low-dimensional feature vectors;

[0107] The numerically simulated data after order reduction (obtained by further numerical simulation through a simplified mechanism network) usually contains multiple variables such as temperature and concentration. Directly using these high-dimensional data for modeling may lead to problems such as excessive model complexity and feature redundancy. Therefore, the present invention first performs normalization preprocessing on each variable to ensure that they are within the same dimension range. Next, the dimensionality reduction of the normalized data is performed by the principal component analysis (PCA) method. The specific steps include:

[0108] S401: Perform normalization preprocessing on the numerically simulated data after order reduction to obtain normalized data;

[0109] The present invention adopts a scaling method in the data preprocessing stage and compares common normalization techniques (such as standardization, Min-Max normalization, and Pareto method). Research shows that the Pareto normalization method can better retain the relative differences and main variation information between variables while effectively scaling the data, avoiding the adverse effects of extreme values on the overall feature extraction. Therefore, the present invention preferably uses the Pareto normalization method to standardize the multi-variable numerical data (including temperature, concentration, etc.) generated after mechanism order reduction, so as to provide a more stable and representative low-dimensional feature vector for subsequent principal component analysis and dimensionality reduction.

[0110] S402: Perform dimensionality reduction on the normalized data through principal component analysis to obtain a low-dimensional feature vector.

[0111] Perform dimensionality reduction on the normalized data by the PCA method, calculate the principal components and loading coefficients, and screen out the key variables that make the main contributions to the system response to form a low-dimensional feature vector.

[0112] Specifically, by solving the eigenvalue problem of the covariance matrix the main features of the data can be extracted. Let be the data matrix after normalization preprocessing, and its covariance matrix is defined as:

[0113]

[0114] where, represents the number of samples, represents the eigenvector matrix, represents the largest eigenvalue, represents the transpose matrix of the eigenvector matrix.

[0115] By performing eigenvalue decomposition on the covariance matrix the respective principal components and their corresponding importance can be obtained. Usually, the first A main component constitutes a low-dimensional feature vector after dimensionality reduction for subsequent machine learning modeling.

[0116] S5: Input the low-dimensional feature vector into a pre-trained comprehensive mapping model for prediction to obtain the prediction result of the key combustion parameters.

[0117] In this embodiment, the present invention proposes a multi-model fusion prediction framework. This framework constructs a basic prediction model using multiple regression techniques and integrates them through a non-linear combination method to form a comprehensive mapping model that has undergone strict cross-validation. It can accurately capture the multi-scale and non-linear coupling relationships in complex reaction processes and achieve real-time prediction of key combustion parameters.

[0118] The specific implementation is as follows:

[0119] (1) A candidate model library including linear regression, ridge regression, decision tree, random forest, and neural network, etc., is constructed. Each model has its own advantages in terms of modeling accuracy, generalization ability, and fitting ability for non-linear relationships. In the specific prediction process, it does not simply perform equal-weight fusion on all models, but quantitatively evaluates the performance of candidate models through performance evaluation indicators, and determines the corresponding fusion weights based on their prediction errors in the historical dataset. For samples in different working intervals or data sub-spaces, the present invention also supports a local adaptive strategy to dynamically select the optimal sub-model combination to improve the prediction accuracy.

[0120] Furthermore, dynamic selection is based on the average error obtained from cross-validation to evaluate the generalization ability of each candidate model on different data sub-spaces. The smaller the average error, the stronger the generalization ability of the model on this data sub-space. The smaller the average error, the greater the weight of the model in subsequent combinations. Sub-model combination: Assign a weight to each selected model, and the final prediction result is the weighted sum of the prediction results of each model. The weight can be determined according to the average error of cross-validation, and the model with a smaller error has a higher weight.

[0121] (2) Construct a comprehensive mapping model based on the candidate model library. To improve the generalization ability of the comprehensive mapping model and avoid overfitting problems, all candidate models are trained and evaluated for performance using k-fold cross-validation. The specific method includes: First, perform dimensionality reduction on the original multi-dimensional data to extract the main component variables representing the system evolution characteristics; Second, calculate the error indicators for each candidate model on the training set and the validation set respectively, and comprehensively use the evaluation results of all cross-validation rounds as the basis for optimizing the fusion weights; Finally, determine the contribution ratio of each candidate model in the fusion process through an adaptive optimization method to construct a comprehensive mapping model with global prediction ability. This comprehensive model is expressed through non-linear combination as:

[0122]

[0123] Among them, represents the final prediction result, represents the total number of candidate models, represents the th candidate model's predicted output for the input , represents the th candidate model's fusion weight, satisfying .

[0124] (3) Input the low-dimensional feature vector into the comprehensive mapping model for prediction, and output the time series prediction results of key combustion parameters. In the model inference stage, the system uses the preprocessed and dimension-reduced low-dimensional feature vector as the input, which includes parameters closely related to the plasma-combustion coupling process such as species concentration and reaction temperature. Each candidate model in the comprehensive mapping model receives the same input and independently outputs the prediction result. Subsequently, the corresponding output is weighted according to the weight parameters of each trained candidate model to form the final predicted value. The system output includes the time series prediction results of key combustion parameters, such as temperature evolution and main species concentration. Using the time series prediction results as the input, drive the digital twin model of the zero-carbon power system to simulate the combustion behavior under different working conditions and accelerate the design iteration (reduce the cost of physical experiments).

[0125] (4) Determine the accuracy of the final prediction result of the comprehensive mapping model and adaptively update the model.

[0126] By dynamically monitoring the error between the final prediction result and the real data, and using various metrics such as mean square error (MSE) and mean absolute error (MAE), determine the prediction accuracy of the model under the current working condition. If the fusion model performs excellently in historical cross-validation and real-time monitoring, and the error metrics are stable within the set threshold, it is regarded as the overall optimal prediction model.

[0127] In summary, while ensuring the integrity of the key combustion reaction mechanism, the present invention realizes efficient order reduction and data-driven prediction, significantly improves the efficiency and accuracy of digital modeling and real-time simulation, and provides strong technical support for the intelligent control, online monitoring and optimal design of the zero-carbon power system.

[0128] Embodiment 2

[0129] This embodiment discloses a zero-carbon power system modeling system based on closed-loop feedback optimized order reduction, including:

[0130] A data acquisition module, which is configured to: acquire the chemical reaction mechanism network and its multi-dimensional data of the zero-carbon power system;

[0131] A mechanism reduction module, which is configured to: perform mechanism reduction on a chemical reaction mechanism network based on the multi-dimensional data to obtain a key reaction path;

[0132] A closed-loop feedback optimization module, which is configured to: construct an energy network based on the key reaction path, perform dynamic layout on the energy network using an improved dynamic force model to obtain a dynamic energy network; optimize the dynamic energy network using a closed-loop feedback mechanism to obtain a simplified mechanism network;

[0133] A feature extraction module, which is configured to: obtain multi-dimensional data of the simplified mechanism network and perform preprocessing, and perform principal component analysis on the preprocessed multi-dimensional data to obtain a low-dimensional feature vector;

[0134] A model prediction module, which is configured to: input the low-dimensional feature vector into a pre-trained comprehensive mapping model for prediction to obtain a prediction result of key combustion parameters.

[0135] Embodiment III

[0136] The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method in Embodiment I are implemented.

[0137] Embodiment IV

[0138] The purpose of this embodiment is to provide a computer-readable storage medium. A computer-readable storage medium has a computer program stored thereon. When the program is executed by a processor, the steps of the method in Embodiment I are executed.

[0139] The steps involved in the devices in the above Embodiments III and IV correspond to those in Method Embodiment I. For specific implementation manners, reference may be made to the relevant description part of Embodiment I. The term "computer-readable storage medium" should be understood to include a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0140] Those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general-purpose computer device. Optionally, they can be implemented by program codes executable by a computing device. Thus, they can be stored in a storage device for execution by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0141] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0142] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that, based on the technical solutions of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A zero-carbon power system modeling method based on closed-loop feedback optimization for order reduction, characterized in that, Including: Obtaining the chemical reaction mechanism network of the zero-carbon power system and its multi-dimensional data; Reducing the mechanism of the chemical reaction mechanism network based on the multi-dimensional data to obtain the key reaction path; Constructing an energy network based on the key reaction path, and performing dynamic layout on the energy network using an improved dynamic force model to obtain a dynamic energy network; Optimizing the dynamic energy network using a closed-loop feedback mechanism to obtain a simplified mechanism network; Obtaining the multi-dimensional data of the simplified mechanism network based on the simplified mechanism network and performing preprocessing, and performing principal component analysis on the preprocessed multi-dimensional data to obtain low-dimensional feature vectors; Inputting the low-dimensional feature vectors into a pre-trained comprehensive mapping model for prediction to obtain the prediction results of key combustion parameters; Introducing an energy-sensitive force mechanism into the ForceAtlas2 model to obtain an improved dynamic force model, including a repulsive force model, an attractive force model, and a random perturbation term; The specific closed-loop feedback mechanism is as follows: Performing spatial layout on the energy network using the improved dynamic force model, visualizing and sorting the species nodes according to the reaction intensity and influence to obtain the node importance ranking; Calibrating the high-importance nodes based on the node importance ranking, and calculating the average distance between each pair according to the spatial coordinates of the high-importance nodes; Adjusting the error threshold in the directed graph method with plasma band error propagation based on the average distance using a feedback adjustment strategy, and performing mechanism reduction based on the adjusted error threshold; Iterating the above steps, and when the error thresholds of all species nodes meet the convergence condition, stop the closed-loop and output the simplified mechanism network.

2. The zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction according to claim 1, wherein Performing mechanism reduction on the chemical reaction mechanism network using the directed graph method with plasma band error propagation, calculating the direct interaction coefficients between species and each energy branch variable, and when the direct interaction coefficient is less than the set error threshold, removing the corresponding species and their related redundant reactions to obtain a skeletal mechanism.

3. The zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction according to claim 2, wherein First, traverse the skeletal mechanism using depth-first search to automatically identify the key reaction path, and then recheck the remaining reaction paths in combination with reaction path analysis.

4. The zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction as claimed in claim 1, wherein, Constructing an energy network based on the key reaction path specifically means: constructing a visualization network based on the key reaction path, and stratifying different species in the visualization network based on the energy type of the species to obtain an energy network.

5. The zero-carbon power system modeling method based on closed-loop feedback optimization and order reduction according to claim 1, characterized in that, Forming a comprehensive mapping model based on a multi-model fusion prediction framework, specifically: Constructing a candidate model library containing multiple candidate models; All candidate models are adopted to be trained and performance-evaluated by the k-fold cross-validation method, and the fusion weights of each candidate model are obtained based on the performance evaluation; Constructing a comprehensive mapping model based on each candidate model and the corresponding fusion weights.

6. A zero-carbon power system modeling system for optimizing reduced order based on closed-loop feedback, characterized in that, Including: A data acquisition module configured to: obtain the chemical reaction mechanism network of the zero-carbon power system and its multi-dimensional data; A mechanism reduction module configured to: reduce the mechanism of the chemical reaction mechanism network based on the multi-dimensional data to obtain the key reaction path; A closed-loop feedback optimization module configured to: construct an energy network based on the key reaction path, perform dynamic layout on the energy network using an improved dynamic force model to obtain a dynamic energy network; optimize the dynamic energy network using a closed-loop feedback mechanism to obtain a simplified mechanism network; A feature extraction module, which is configured to: obtain multi-dimensional data based on the simplified mechanism network and perform preprocessing, and perform principal component analysis on the preprocessed multi-dimensional data to obtain a low-dimensional feature vector; A model prediction module, which is configured to: input the low-dimensional feature vector into a pre-trained comprehensive mapping model for prediction to obtain a prediction result of key combustion parameters; An energy-sensitive force mechanism is introduced into the ForceAtlas2 model to obtain an improved dynamic force model, including a repulsive force model, an attractive force model, and a random perturbation term; The specific closed-loop feedback mechanism is as follows: Use the improved dynamic force model to perform spatial layout on the energy network, visually sort the species nodes according to the reaction intensity and influence, and obtain the node importance ranking; Calibrate the high-importance nodes based on the node importance ranking, and calculate the average distance between each pair according to the spatial coordinates of the high-importance nodes; Based on the average distance, use a feedback adjustment strategy to adjust the error threshold in the directed relationship graph method with plasma band error propagation, and perform mechanism reduction based on the adjusted error threshold; Iterate the above steps, and when the error thresholds of all species nodes meet the convergence conditions, stop the closed loop and output the simplified mechanism network.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps in the zero-carbon power system modeling method based on closed-loop feedback optimization and reduction as described in any one of claims 1-5.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the zero-carbon power system modeling method based on closed-loop feedback optimization and reduction as described in any one of claims 1-5.

Images