Formula optimization method, device and equipment of liquid impregnant for power capacitor and medium

Abstract

The invention discloses a formula optimization method and device of a liquid impregnant for a power capacitor, equipment and a medium, and relates to the technical field of computers. Comprising the following steps: determining basic structure parameters based on molecular structure data of impregnant molecules, and calculating structure indexes for representing an inspiration mechanism based on the basic structure parameters; constructing an initial model based on the structure indexes, and adjusting weight parameters of the model to obtain an inspiration scoring model; the inspiration scoring model comprises a first-layer model for outputting an inspiration active site score and a second-layer model for outputting a structural inspiration score; determining an inspiration score of the to-be-evaluated impregnant molecule based on the structure index of the to-be-evaluated impregnant molecule by using an inspiration scoring model; and determining the inspiration performance of the to-be-evaluated impregnant molecule based on the inspiration score, and optimizing the formula of the to-be-evaluated impregnant molecule based on the inspiration performance. Therefore, the evaluation efficiency of the air suction performance of the impregnant can be improved, and screening and formula optimization of liquid impregnant molecules are realized.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, equipment, and medium for optimizing the formulation of liquid impregnating agents for power capacitors. Background Technology

[0002] In high-voltage power capacitors, liquid impregnating agents play a crucial role in filling the voids in the solid dielectric, providing electrical insulation, and dissipating heat. Under strong electric fields and thermal stress environments, liquid impregnating agents are prone to decomposition or electrochemical reactions, releasing small molecule gases such as hydrogen. If the impregnating agent lacks sufficient getter properties, these released gases can aggregate into microbubbles, leading to breakdown and damage to the capacitor element. Therefore, the getter properties of the impregnating agent are critical to its long-term stable operation.

[0003] Currently, the evaluation of the getter performance of liquid impregnating agents mainly employs two types of methods: one is based on standardized experimental testing methods, such as measuring gas volume changes under a high-voltage electric field to evaluate the macroscopic gas absorption and desorption trends of the liquid using the getter coefficient. These methods involve complex equipment, long testing cycles, and results that are sensitive to operating conditions, and they struggle to reveal the microscopic mechanisms of getter behavior. The other type is based on semi-empirical methods using physicochemical correlations, such as establishing statistical relationships between structural parameters like aromatic carbon content and carbon form analysis and getter performance. However, these methods primarily target traditional mineral oil components and are difficult to apply to novel impregnating agents such as environmentally friendly esters, and they also cannot provide quantitative evaluation of single molecular structures. Furthermore, while partial discharge and lifetime tests based on model capacitors can comprehensively verify the getter performance of impregnating agent systems, they suffer from long testing cycles and high costs, making them unsuitable for rapid screening and comparison of a large number of candidate molecules in the early stages.

[0004] As can be seen from the above, improving the evaluation efficiency of the gas absorption performance of impregnating agents and achieving the screening of liquid impregnating agent molecules and formulation optimization is an urgent problem to be solved. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a method, apparatus, equipment, and medium for optimizing the formulation of liquid impregnating agents for power capacitors, which can improve the evaluation efficiency of the impregnating agent's getter performance and achieve the screening and formulation optimization of liquid impregnating agent molecules. The specific solution is as follows: In a first aspect, this application provides a method for optimizing the formulation of a liquid impregnating agent for power capacitors, comprising: The basic structural parameters are determined based on the molecular structure data of the impregnating agent molecules, and structural indices used to characterize the inhalation mechanism are calculated based on these basic structural parameters; the basic structural parameters include the total number of carbon atoms, the number of aromatic atoms, the number of double bonds, and the maximum number of carbon atoms. The number of atoms, atomic polarizability, and molecular weight of the conjugated system; the structural indices include aromatic carbon fraction, unsaturation density, relative size of the conjugated system, and polarizability per unit mass. An initial model is constructed based on the structural indices, and the weight parameters of the initial model are adjusted to obtain an inhalation scoring model. The inhalation scoring model includes a first-layer model for outputting the score of inhaled active sites and a second-layer model for outputting the structural inhalation score. The output of the first-layer model is connected to the input of the second-layer model, and the structural inhalation score is an inhalation score related to molecular structural features. The upgassing score of the impregnating agent molecule to be evaluated is determined based on the structural indices of the impregnating agent molecule using the aforementioned upgassing scoring model. The gas absorption performance of the impregnating agent molecule to be evaluated is determined based on the gas absorption score, and the formulation of the impregnating agent molecule to be evaluated is optimized based on the gas absorption performance.

[0006] Optionally, the calculation of structural indices characterizing the inhalation mechanism based on the basic structural parameters includes: The aromatic carbon fraction is calculated based on the total number of carbon atoms and the number of aromatic atoms, using the following formula: ;in, The aromatic carbon fraction is used to characterize the proportion of aromatic carbons in all carbon atoms. The number of aromatic atoms, The total number of carbon atoms; The unsaturation density is calculated based on the total number of carbon atoms and the number of double bonds, using the following formula: ;in, Unsaturation density is used to characterize the number of unsaturated bonds per unit carbon skeleton. Number of double bonds; Based on the total number of carbon atoms and the maximum The relative size of the conjugated system is obtained by calculating the number of atoms in the conjugated system, using the following formula: ;in, The relative size of the conjugate system is used to characterize the maximum. The relative size of the conjugated system within the entire molecule. To the maximum Number of atoms in a conjugated system; The polarization capability per unit mass is calculated based on atomic polarizability and the molecular weight, using the following formula: ;in, Polarization capability per unit mass is used to represent the polarization response of molecules under an electric field. denoted by and MW by , where MW is the molecular weight.

[0007] Optionally, adjusting the weight parameters of the initial model to obtain the inspiratory scoring model includes: Acquire several sample molecules with known measured inspiratory performance data, and use the initial model to calculate the initial score of the sample molecules based on the structural indices of the sample molecules; With the goal of minimizing the difference between the initial score and the measured inhalation performance data, the weight parameters are optimized and adjusted under preset constraints to obtain an inhalation score model.

[0008] Optionally, the preset constraints include the non-negative weight parameters corresponding to each structural index; In the first layer model, the sum of the weight parameters corresponding to the unsaturation density, aromatic carbon fraction and relative size of the conjugated system is 1. The weight parameter corresponding to the aromatic carbon fraction is constrained within a preset first value range. The weight parameter corresponding to the unsaturation density is not less than a preset first lower limit value. The weight parameter corresponding to the relative size of the conjugated system is not less than a preset second lower limit value. In the second-layer model, the sum of the weight parameters corresponding to the inspiratory active site fraction and the unit mass polarization capability is 1, and the weight parameters corresponding to the inspiratory active site fraction are constrained within a preset second value range.

[0009] Optionally, determining the upgassing score of the impregnating agent molecule based on its structural indices using the upgassing scoring model includes: The structural indices of the impregnating agent molecules to be evaluated are normalized to obtain normalized structural indices. The first-layer model is used to perform a weighted summation of the normalized unsaturation density, aromatic carbon fraction, and relative size of the conjugated system based on the weight parameters to obtain the corresponding inhalation active site fraction. The second-layer model is used to perform a weighted summation of the inhaled active site score and the normalized unit mass polarization capability based on the weight parameters, so as to obtain the structure-inhaled score of the impregnating agent molecule to be evaluated.

[0010] Optionally, the normalization of the structural indices of the impregnating agent molecule to be evaluated to obtain normalized structural indices includes: The global maximum value of the structural index of the impregnating agent molecule to be evaluated is obtained based on a preset calibration molecule set, and the structural index of the impregnating agent molecule to be evaluated is normalized using the global maximum value to obtain the normalized structural index.

[0011] Optionally, determining the uptake performance of the impregnating agent molecule to be evaluated based on the uptake score includes: The inhalation score of the impregnating agent molecule to be evaluated is compared with a preset scoring threshold range to determine its inhalation performance level. And / or, sort the upgassing scores of multiple impregnating agent molecules to be evaluated.

[0012] Secondly, this application provides a formulation optimization device for a liquid impregnating agent for power capacitors, comprising: The parameter determination module is used to determine basic structural parameters based on the molecular structure data of the impregnating agent molecules, and to calculate structural indices characterizing the inhalation mechanism based on the basic structural parameters; the basic structural parameters include the total number of carbon atoms, the number of aromatic atoms, the number of double bonds, and the maximum number of carbon atoms. The number of atoms, atomic polarizability, and molecular weight of the conjugated system; the structural indices include aromatic carbon fraction, unsaturation density, relative size of the conjugated system, and polarizability per unit mass. The model building module is used to build an initial model based on the structural indicators and adjust the weight parameters of the initial model to obtain an inspiratory scoring model; the inspiratory scoring model includes several layers of computational models. The evaluation module is used to determine the inhalation score of the impregnating agent molecule to be evaluated based on the structural index of the impregnating agent molecule using the inhalation scoring model. The formulation optimization module is used to determine the uptake performance of the impregnating agent molecule to be evaluated based on the uptake score, and to optimize the formulation of the impregnating agent molecule to be evaluated based on the uptake performance.

[0013] Thirdly, this application provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the aforementioned method for optimizing the formulation of liquid impregnating agents for power capacitors.

[0014] Fourthly, this application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned method for optimizing the formulation of a liquid impregnating agent for power capacitors.

[0015] This application provides a method for optimizing the formulation of a liquid impregnating agent for power capacitors. The method involves determining basic structural parameters based on the molecular structure data of the impregnating agent molecule, and calculating structural indices characterizing the upgassing mechanism based on these parameters. An initial model is constructed based on these structural indices, and the weight parameters of the initial model are adjusted to obtain an upgassing scoring model. The upgassing scoring model includes a first-layer model for outputting the score of upgassing active sites and a second-layer model for outputting the structural upgassing score. The output of the first-layer model is connected to the input of the second-layer model, and the structural upgassing score is an upgassing score related to molecular structural characteristics. The upgassing score of the impregnating agent molecule to be evaluated is determined using the upgassing scoring model based on its structural indices. The upgassing performance of the impregnating agent molecule to be evaluated is determined based on the upgassing score, and the formulation of the impregnating agent molecule to be evaluated is optimized based on the upgassing performance.

[0016] As can be seen from the above, this application can achieve rapid and quantitative prediction and comparison of the uptake performance of liquid impregnating agent molecules based solely on molecular structure data by constructing and optimizing a two-layer weighted scoring model. This avoids the complexity and high cost of traditional experimental evaluation methods and overcomes the limitation of existing empirical models being unsuitable for novel environmentally friendly ester impregnating agents. Therefore, it can improve the evaluation efficiency of the uptake performance of impregnating agents and achieve the screening and formulation optimization of liquid impregnating agent molecules. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 This is a flowchart of a method for optimizing the formulation of a liquid impregnating agent for power capacitors disclosed in this invention; Figure 2 This is a schematic diagram of a formulation optimization device for a liquid impregnating agent for power capacitors disclosed in this invention; Figure 3 This is a structural diagram of an electronic device disclosed in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] In high-voltage power capacitors, liquid impregnating agents play a crucial role in filling the voids in the solid dielectric, providing electrical insulation, and dissipating heat. Under strong electric fields and thermal stress environments, liquid impregnating agents are prone to decomposition or electrochemical reactions, releasing small molecule gases such as hydrogen. If the impregnating agent lacks sufficient getter properties, these released gases will aggregate into microbubbles, causing breakdown and damage to the capacitor components. Therefore, the getter properties of the impregnating agent are crucial for its long-term stable operation. Currently, the evaluation of the getter properties of liquid impregnating agents mainly employs two types of methods: one is based on standardized experimental testing methods, such as measuring the gas volume change under a high-voltage electric field to evaluate the macroscopic gas absorption and release trend of the liquid using the getter coefficient. These methods involve complex equipment, long testing cycles, and results that are sensitive to operating conditions, and they are difficult to reveal the microscopic mechanisms of getter behavior. The other type is based on semi-empirical methods using physicochemical correlations, such as establishing statistical relationships between structural parameters such as aromatic carbon content and carbon type analysis and getter properties. However, these methods are mainly for traditional mineral oil components and are difficult to apply to new impregnating agents such as environmentally friendly esters, and they cannot provide quantitative evaluation of single molecular structures. Furthermore, while partial discharge and lifetime tests based on model capacitors can comprehensively verify the getter performance of the impregnating agent system, they suffer from long testing cycles and high costs, making them unsuitable for rapid screening and comparison of a large number of candidate molecules in the early stages. Therefore, this application provides a formulation optimization scheme for liquid impregnating agents used in power capacitors, which can improve the evaluation efficiency of the getter performance of impregnating agents and realize the screening and formulation optimization of liquid impregnating agent molecules.

[0021] See Figure 1 As shown in the embodiments of this application, a method for optimizing the formulation of a liquid impregnating agent for power capacitors is disclosed, including: Step S11: Determine the basic structural parameters based on the molecular structure data of the impregnating agent molecules, and calculate the structural indices used to characterize the inhalation mechanism based on the basic structural parameters.

[0022] In this embodiment, the structural information of the candidate impregnating agent molecules is first obtained. This information can typically be derived using molecular modeling software (such as Gaussian, Materials Studio, etc.), cheminformatics databases, or based on known chemical formulas and configurations.

[0023] Furthermore, based on molecular structure, six fundamental structural parameters are extracted or calculated: the total number of carbon atoms (nC), used to characterize the molecular skeleton scale, serves as a benchmark for converting other "count-type" descriptors into "density-type" indicators. Normalization using nC eliminates simple size effects between chains of different lengths and molecular weights, allowing molecules of different sizes to be compared on a unified scale regarding their upgassing site "density".

[0024] The number of aromatic atoms (naAromAtom, usually referring to the number of carbon atoms on the aromatic ring) is used to record the number of atoms on the aromatic ring in a molecule. It mainly consists of aromatic carbon. The higher the content of aromatic carbon in mineral oil and aromatic impregnating agents, the stronger the oil's ability to absorb hydrogen and reduce gas evolution. Polycyclic aromatic structures such as benzyltoluene and dibenzyltoluene exert their gas absorption effect precisely by means of the aromatic skeleton and benzylic structure.

[0025] The number of double bonds (nBondsD2, including unsaturated bonds such as carbon-carbon double bonds) is used to reflect the number of double bonds in a molecule. For natural esters and unsaturated synthetic esters, carbon-carbon double bonds and carbon-oxygen double bonds are usually the main sites for hydrogen addition and free radical reactions. The higher the degree of unsaturation, the more potential uptake sites there are.

[0026] maximum The number of conjugated system atoms (nAtomP, i.e., the total number of atoms contained in the longest continuous conjugated system in a molecule) is used to describe the number of atoms contained in the largest π-conjugated system in a molecule, and can distinguish structural types such as monocyclic aromatics, bicyclic aromatics, and long conjugated chains. Bicyclic aromatics and long conjugated systems have stronger delocalization stability for free radical intermediates and charged particles, and therefore have better gas uptake ability.

[0027] Atomic polarizability (apol, obtained by summing the polarizabilities of individual atoms, commonly estimated using computational chemistry or group contribution methods) represents the sum of the polarizabilities of all atoms in a molecule, reflecting the deformability of the electron cloud and the strength of dispersive interactions. Molecules with high polarizability are more likely to generate induced dipoles in an electric field, forming instantaneous interactions with hydrogen, free radicals, and electrons, which is beneficial for gas dissolution and adsorption, and is an important parameter characterizing physical gas uptake capability.

[0028] Molecular weight (MW) does not directly determine the uptake, but it is used as a normalization benchmark for apol. It can convert the total polarizability into the polarizability per unit mass, weaken the size effect of "the larger the molecule, the larger the apol", and thus more fairly compare the polarizability of molecules of different sizes.

[0029] After obtaining the above six basic parameters, four core structural indicators are further calculated. Specifically, the calculation of structural indicators for characterizing the inhalation mechanism based on the basic structural parameters may include: The aromatic carbon fraction is calculated based on the total number of carbon atoms and the number of aromatic atoms, using the following formula: ; in, The aromatic carbon fraction is used to characterize the proportion of aromatic carbons in all carbon atoms. The number of aromatic atoms, This represents the total number of carbon atoms. This indicator reflects the proportion of aromatic structures in the molecule; a high content of aromatic carbons usually means stronger free radical scavenging and hydrogen adsorption capabilities.

[0030] The unsaturation density is calculated based on the total number of carbon atoms and the number of double bonds, using the following formula: ; in, Unsaturation density is used to characterize the number of unsaturated bonds per unit carbon skeleton. The number of double bonds represents the density of unsaturated bonds per unit carbon skeleton and is directly related to the number of potential sites for the molecule to consume small gas molecules such as hydrogen through addition reactions.

[0031] Based on the total number of carbon atoms and the maximum The relative size of the conjugated system is obtained by calculating the number of atoms in the conjugated system, and the calculation formula is shown below: ; in, The relative size of the conjugate system is used to characterize the maximum. The relative size of the conjugated system within the entire molecule. To the maximum Number of atoms in the conjugated system. This indicator is used to quantify the relative size of the largest π-conjugated system in a molecule. Large-scale conjugated systems are beneficial for stabilizing reaction intermediates and enhancing chemisorption.

[0032] The polarization capability per unit mass is calculated based on atomic polarizability and the molecular weight, as shown in the following formula: ; in, Polarization capability per unit mass is used to represent the polarization response of molecules under an electric field. Σ(m) represents atomic polarizability, and MW represents molecular weight. This index reflects the polarizability of a unit mass molecule and is related to the physical solubility and adsorption capacity of the gas in the medium.

[0033] Step S12: Construct an initial model based on the structural indicators and adjust the weight parameters of the initial model to obtain an inhalation scoring model.

[0034] In this embodiment, an initial model framework is constructed. This framework consists of a first-layer model and a second-layer model connected in series. The inspiratory scoring model includes a first-layer model for outputting the score of inspiratory active sites and a second-layer model for outputting the structural inspiratory score; the structural inspiratory score is an inspiratory score related to molecular structural features. It should be noted that, to eliminate the influence of dimensions, the four inputs to the model need to be adjusted. Structural indices are normalized. For example, in one specific implementation, a "global maximum value normalization method" can be used. Specifically, the normalization of the structural indices of the impregnating agent molecule to be evaluated to obtain normalized structural indices may include: obtaining the global maximum value of the structural indices of the impregnating agent molecule to be evaluated based on a preset calibration molecule set, and using the global maximum value to normalize the structural indices of the impregnating agent molecule to be evaluated to obtain normalized structural indices. That is, firstly, the global maximum value of each structural indices is calculated based on a comprehensive calibration molecule set (which may contain a large number of candidate molecules with known structures), and then the normalized value of the structural indices of any molecule is calculated based on the global maximum value, as shown in the following formula: ; ; ;

[0035] in, , , , These represent the normalized unsaturation density, aromatic carbon fraction, relative size of the conjugated system, and polarization capacity per unit mass, respectively. , , , These represent the global maximum values ​​of unsaturation density, aromatic carbon fraction, relative size of the conjugated system, and polarization capability per unit mass, respectively.

[0036] In this embodiment, the inputs to the first-layer model are the normalized unsaturation density, aromatic carbon fraction, and relative size of the conjugated system, and the output is the fraction of uptake active sites, calculated as follows: ; in, This represents the fraction of inspiratory active sites. These parameters represent the weights of the unsaturation density, aromatic carbon fraction, and relative size of the conjugated system on the overall contribution of the inhalation active sites, respectively. Initial values ​​can be set based on domain knowledge, such as prior knowledge of the contributions of aliphatic unsaturated bonds, aromatic structures, and conjugated systems during inhalation. And the sum of the three is 1.

[0037] The input to the first-layer model is the inspiratory active site score output from the first layer and the normalized polarization per unit mass. The output is the final structural inspiratory score, calculated as follows: ; in, For the final structural inhalation score, The weighted parameters, representing the inspiratory active sites and the polarization capacity per unit mass, are typically set to satisfy the following initial values: This is to reflect the dominant role of the chemical getter site, and the sum of the two is 1.

[0038] In this embodiment, the model is equivalent to a weighted summation of four normalized structural indices through the above two-layer linear combination. However, the two-layer structure can control the weights of the "inhalation site level" and the "physical adsorption level" respectively, which makes it easier to introduce different mechanism prior constraints.

[0039] Furthermore, the model weight parameters are adjusted to optimize the model. The initial weight values ​​are estimates based on mechanistic understanding and need to be calibrated with experimental data to obtain a more universal inspiratory scoring model. Specifically, adjusting the weight parameters of the initial model to obtain the inspiratory scoring model may include: collecting a set of molecules with known and reliable measured inspiratory performance data (e.g., inspiratory coefficients measured by GB / T standard tests) as samples. These samples should cover as many different types of impregnating agents as possible (e.g., aromatic oils, unsaturated esters, etc.) and different inspiratory performance levels; normalizing the four structural indices of the sample molecules through the aforementioned steps, and using the normalized structural indices to minimize the difference between the model's predicted score and the measured data as the optimization objective, optimizing and adjusting the weight parameters to obtain the inspiratory scoring model.

[0040] It is important to note that constraints need to be applied to prevent the optimization process from deviating from the physical meaning. Specifically, the preset constraints include non-negative weight parameters corresponding to each structural index; in the first-layer model, the sum of the weight parameters corresponding to unsaturation density, aromatic carbon fraction, and the relative size of the conjugated system is 1, to ensure that the contribution of each structural factor to uptake is non-negative and weighted; the weight parameter corresponding to aromatic carbon fraction is constrained within a preset first value range to avoid excessive reduction or amplification of aromaticity contribution when the sample is limited; the weight parameter corresponding to unsaturation density is not less than a preset first lower limit, and the weight parameter corresponding to the relative size of the conjugated system is not less than a preset second lower limit, to ensure that unsaturation and conjugation account for a reasonable proportion in the total site contribution; in the second-layer model, the sum of the weight parameters corresponding to the fraction of uptake active sites and the polarization capacity per unit mass is 1, and the weight parameter corresponding to the fraction of uptake active sites is constrained within a preset second value range to ensure that the overall performance is still dominated by chemical sites. The above optimization problem is solved using constrained optimization algorithms (such as Sequential Quadratic Programming (SQP) and Generalized Reducing Gradient Method (GRG)) to obtain a set of optimal weight parameters. This set of parameters defines the final, calibrated inhalation scoring model. It is understood that the preset first lower limit, preset second lower limit, preset first value range, and preset second value range can be determined based on the actual application scenario, and are not specifically limited here.

[0041] Step S13: Determine the air-intake score of the impregnating agent molecule to be evaluated based on the structural index of the impregnating agent molecule using the air-intake scoring model.

[0042] In this embodiment, for any new impregnating agent molecule to be evaluated, the corresponding six basic parameters are obtained based on the aforementioned steps, and its four original structural indices are calculated. The normalized indices are then substituted into the determined, parameter-fixed updraft scoring model to determine the updraft score of the impregnating agent molecule to be evaluated.

[0043] Step S14: Determine the gas absorption performance of the impregnating agent molecule to be evaluated based on the gas absorption score, and optimize the formulation of the impregnating agent molecule to be evaluated based on the gas absorption performance.

[0044] In this embodiment, after obtaining the upgassing score of the impregnating agent molecule to be evaluated, a large number of candidate impregnating agent molecules can be sorted according to the score. Combined with the score ranges of pre-calibrated typical samples (such as MBT, DBT, and several strong / medium / weak upgassing reference molecules), new molecules are divided into different upgassing level grades for rapid evaluation and quantitative screening of the upgassing performance of impregnating agent molecules. Among numerous candidate molecules (which can be existing compound libraries or virtually designed molecules), the score of each molecule is calculated and sorted from high to low. Molecules with higher scores have better predicted upgassing performance and can be considered as priority candidates.

[0045] Furthermore, guiding formulation design and optimization includes directly selecting the single compound with the highest score as the target impregnating agent or its main component. When multiple components need to be blended, the scores of each pure component can be calculated. Components with higher scores are preferred for blending. Simultaneously, for the initial evaluation of mixtures, a weighted average of the component scores (based on mole fraction or volume fraction) can be used as an approximate estimate of the mixture score, providing preliminary guidance for blending ratios. By analyzing the structural characteristics of high-scoring molecules, favorable combinations of molecular descriptors can be summarized. In molecular design, these structural features can be purposefully introduced or enhanced (e.g., increasing the number of double bonds, introducing aromatic rings, expanding conjugated systems, selecting groups with high polarizability) to improve the predicted upgas score of the final molecule, achieving performance-oriented rational molecular design.

[0046] As can be seen from the above, the embodiments of this application construct a structure scoring model that takes into account aliphatic unsaturated sites, aromatic skeletons, conjugated systems, and polarization capabilities based on a small number of molecular descriptors with clear physical meaning. Under the constraint of mechanism, the weights are semi-empirically corrected using a small amount of experimental data. This maintains the interpretability of the model and its robustness under small sample conditions. After the parameters are determined, it can be directly used for rapid scoring and ranking of any candidate molecules, which can significantly reduce blind experimental screening work. It provides a direct and reliable theoretical basis and computational tool for the rational molecular design, efficient screening, and formulation optimization of high-performance impregnating agents.

[0047] See Figure 2 As shown in the figure, this application discloses a formulation optimization device for a liquid impregnating agent for power capacitors, comprising: The parameter determination module 11 is used to determine basic structural parameters based on the molecular structure data of the impregnating agent molecules, and to calculate structural indices characterizing the inhalation mechanism based on the basic structural parameters; the basic structural parameters include the total number of carbon atoms, the number of aromatic atoms, the number of double bonds, and the maximum number of carbon atoms. The number of atoms, atomic polarizability, and molecular weight of the conjugated system; the structural indices include aromatic carbon fraction, unsaturation density, relative size of the conjugated system, and polarizability per unit mass. The model building module 12 is used to build an initial model based on the structural indicators and adjust the weight parameters of the initial model to obtain an inhalation scoring model; the inhalation scoring model includes several layers of calculation models. Evaluation module 13 is used to determine the inhalation score of the impregnating agent molecule to be evaluated based on the structural index of the impregnating agent molecule to be evaluated using the inhalation scoring model; The formulation optimization module 14 is used to determine the air-breathing performance of the impregnating agent molecule to be evaluated based on the air-breathing score, and to optimize the formulation of the impregnating agent molecule to be evaluated based on the air-breathing performance.

[0048] In some specific embodiments, the parameter determination module 11 may specifically include: The first parameter determining unit is used to calculate the aromatic carbon fraction based on the total number of carbon atoms and the number of aromatic atoms, using the following formula: ;in, The aromatic carbon fraction is used to characterize the proportion of aromatic carbons in all carbon atoms. The number of aromatic atoms, The total number of carbon atoms; The second parameter determination unit is used to calculate the unsaturation density based on the total number of carbon atoms and the number of double bonds, using the following formula: ;in, Unsaturation density is used to characterize the number of unsaturated bonds per unit carbon skeleton. Number of double bonds; The third parameter determination unit is used to determine the parameters based on the total number of carbon atoms and the maximum number of carbon atoms. The relative size of the conjugated system is obtained by calculating the number of atoms in the conjugated system, using the following formula: ;in, The relative size of the conjugate system is used to characterize the maximum. The relative size of the conjugated system within the entire molecule. To the maximum Number of atoms in a conjugated system; The fourth parameter determination unit is used to calculate the unit mass polarization capability based on atomic polarizability and the molecular weight, using the following formula: ;in, Polarization capability per unit mass is used to represent the polarization response of molecules under an electric field. denoted by and MW by , where MW is the molecular weight.

[0049] In some specific embodiments, the model building module 12 may specifically include: An initial scoring unit is used to acquire several sample molecules with known measured inspiratory performance data, and to calculate the initial score of the sample molecules based on the structural indices of the sample molecules using the initial model. The model adjustment unit is used to optimize and adjust the weight parameters under preset constraints with the goal of minimizing the difference between the initial score and the measured inhalation performance data, so as to obtain an inhalation score model; the preset constraints include that the weight parameters corresponding to each structural index are non-negative. In the first layer model, the sum of the weight parameters corresponding to the unsaturation density, aromatic carbon fraction and relative size of the conjugated system is 1. The weight parameter corresponding to the aromatic carbon fraction is constrained within a preset first value range. The weight parameter corresponding to the unsaturation density is not less than a preset first lower limit value. The weight parameter corresponding to the relative size of the conjugated system is not less than a preset second lower limit value. In the second-layer model, the sum of the weight parameters corresponding to the inspiratory active site fraction and the unit mass polarization capability is 1, and the weight parameters corresponding to the inspiratory active site fraction are constrained within a preset second value range.

[0050] In some specific embodiments, the evaluation module 13 may specifically include: The data preprocessing submodule is used to normalize the structural indices of the impregnating agent molecules to be evaluated, so as to obtain normalized structural indices. The first data processing unit is used to use the first layer model to perform a weighted summation of the normalized unsaturation density, aromatic carbon fraction and relative size of the conjugated system based on the weight parameters, so as to obtain the corresponding inhalation active site fraction. The second data processing unit is used to use the second layer model to perform a weighted summation of the inhalation active site score and the normalized unit mass polarization capability based on the weight parameters, so as to obtain the structure inhalation score of the impregnating agent molecule to be evaluated. Accordingly, the data preprocessing submodule may specifically include: The data normalization unit is used to obtain the global maximum value of the structural index of the impregnating agent molecule to be evaluated based on a preset calibration molecule set, and to use the global maximum value to normalize the structural index of the impregnating agent molecule to be evaluated, so as to obtain the normalized structural index.

[0051] In some specific embodiments, the formula optimization module 14 may specifically include: The inhalation performance level determination unit is used to compare the inhalation score of the impregnating agent molecule to be evaluated with a preset score threshold range to determine its inhalation performance level. The uptake performance ranking unit is used to rank the uptake scores of multiple impregnating agent molecules to be evaluated.

[0052] Furthermore, embodiments of this application also disclose an electronic device, Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the formulation optimization method for liquid impregnating agents for power capacitors disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0053] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0054] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0055] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the formulation optimization method for the liquid impregnating agent for power capacitors disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0056] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned method for optimizing the formulation of a liquid impregnating agent for power capacitors. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0057] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0058] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0059] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0060] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for optimizing the formulation of a liquid impregnating agent for power capacitors, characterized in that, include: The basic structural parameters are determined based on the molecular structure data of the impregnating agent molecules, and structural indices used to characterize the inhalation mechanism are calculated based on these basic structural parameters; the basic structural parameters include the total number of carbon atoms, the number of aromatic atoms, the number of double bonds, and the maximum number of carbon atoms. The number of atoms, atomic polarizability, and molecular weight of the conjugated system; the structural indices include aromatic carbon fraction, unsaturation density, relative size of the conjugated system, and polarizability per unit mass. An initial model is constructed based on the structural indices, and the weight parameters of the initial model are adjusted to obtain an inhalation scoring model. The inhalation scoring model includes a first-layer model for outputting the score of inhaled active sites and a second-layer model for outputting the structural inhalation score. The output of the first-layer model is connected to the input of the second-layer model, and the structural inhalation score is an inhalation score related to molecular structural features. The upgassing score of the impregnating agent molecule to be evaluated is determined based on the structural indices of the impregnating agent molecule using the aforementioned upgassing scoring model. The gas absorption performance of the impregnating agent molecule to be evaluated is determined based on the gas absorption score, and the formulation of the impregnating agent molecule to be evaluated is optimized based on the gas absorption performance.

2. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 1, characterized in that, The structural indices used to characterize the inhalation mechanism, calculated based on the aforementioned basic structural parameters, include: The aromatic carbon fraction is calculated based on the total number of carbon atoms and the number of aromatic atoms, using the following formula: ;in, The aromatic carbon fraction is used to characterize the proportion of aromatic carbons in all carbon atoms. The number of aromatic atoms, The total number of carbon atoms; The unsaturation density is calculated based on the total number of carbon atoms and the number of double bonds, using the following formula: ;in, Unsaturation density is used to characterize the number of unsaturated bonds per unit carbon skeleton. Number of double bonds; Based on the total number of carbon atoms and the maximum The relative size of the conjugated system is obtained by calculating the number of atoms in the conjugated system, using the following formula: ;in, The relative size of the conjugate system is used to characterize the maximum. The relative size of the conjugated system within the entire molecule. To the maximum Number of atoms in a conjugated system; The polarization capability per unit mass is calculated based on atomic polarizability and the molecular weight, using the following formula: ;in, Polarization capability per unit mass is used to represent the polarization response of molecules under an electric field. denoted by and MW by , where MW is the molecular weight.

3. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 1, characterized in that, The adjustment of the weight parameters of the initial model to obtain the inspiratory scoring model includes: Acquire several sample molecules with known measured inspiratory performance data, and use the initial model to calculate the initial score of the sample molecules based on the structural indices of the sample molecules; With the goal of minimizing the difference between the initial score and the measured inhalation performance data, the weight parameters are optimized and adjusted under preset constraints to obtain an inhalation score model.

4. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 3, characterized in that, The preset constraints include the non-negative weight parameters corresponding to each structural index; In the first layer model, the sum of the weight parameters corresponding to the unsaturation density, aromatic carbon fraction and relative size of the conjugated system is 1. The weight parameter corresponding to the aromatic carbon fraction is constrained within a preset first value range. The weight parameter corresponding to the unsaturation density is not less than a preset first lower limit value. The weight parameter corresponding to the relative size of the conjugated system is not less than a preset second lower limit value. In the second-layer model, the sum of the weight parameters corresponding to the inspiratory active site fraction and the unit mass polarization capability is 1, and the weight parameters corresponding to the inspiratory active site fraction are constrained within a preset second value range.

5. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 1, characterized in that, The step of determining the upgassing score of the impregnating agent molecule to be evaluated based on the structural indices of the impregnating agent molecule using the upgassing scoring model includes: The structural indices of the impregnating agent molecules to be evaluated are normalized to obtain normalized structural indices. The first-layer model is used to perform a weighted summation of the normalized unsaturation density, aromatic carbon fraction, and relative size of the conjugated system based on the weight parameters to obtain the corresponding inhalation active site fraction. The second-layer model is used to perform a weighted summation of the inhaled active site score and the normalized unit mass polarization capability based on the weight parameters, so as to obtain the structure-inhaled score of the impregnating agent molecule to be evaluated.

6. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 5, characterized in that, The normalization of the structural indices of the impregnating agent molecules to be evaluated, to obtain normalized structural indices, includes: The global maximum value of the structural index of the impregnating agent molecule to be evaluated is obtained based on a preset calibration molecule set, and the structural index of the impregnating agent molecule to be evaluated is normalized using the global maximum value to obtain the normalized structural index.

7. The method for optimizing the formulation of the liquid impregnating agent for power capacitors according to claim 1, characterized in that, The determination of the uptake performance of the impregnating agent molecule to be evaluated based on the uptake score includes: The inhalation score of the impregnating agent molecule to be evaluated is compared with a preset scoring threshold range to determine its inhalation performance level. And / or, sort the upgassing scores of multiple impregnating agent molecules to be evaluated.

8. A formulation optimization device for a liquid impregnating agent for power capacitors, characterized in that, include: The parameter determination module is used to determine basic structural parameters based on the molecular structure data of the impregnating agent molecules, and to calculate structural indices characterizing the upgassing mechanism based on the basic structural parameters. The basic structural parameters include the total number of carbon atoms, the number of aromatic atoms, the number of double bonds, the number of atoms in the maximum conjugated system, atomic polarizability, and molecular weight. The structural indices include the aromatic carbon fraction, unsaturation density, relative size of the conjugated system, and polarizability per unit mass. The model building module is used to build an initial model based on the structural indicators and adjust the weight parameters of the initial model to obtain an inspiratory scoring model; the inspiratory scoring model includes several layers of computational models. The evaluation module is used to determine the inhalation score of the impregnating agent molecule to be evaluated based on the structural index of the impregnating agent molecule using the inhalation scoring model. The formulation optimization module is used to determine the uptake performance of the impregnating agent molecule to be evaluated based on the uptake score, and to optimize the formulation of the impregnating agent molecule to be evaluated based on the uptake performance.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the formulation optimization method for liquid impregnating agents for power capacitors as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the formulation optimization method for a liquid impregnating agent for power capacitors as described in any one of claims 1 to 7.

Images