CN116434852A

CN116434852A - Method, device, equipment, storage medium and application for determining lubricating oil production reaction condition

Info

Publication number: CN116434852A
Application number: CN202111656027.2A
Authority: CN
Inventors: 王杭州; 纪晔; 杨诗棋; 王弘历; 边钢月; 刘一心
Original assignee: Petrochina Co Ltd
Current assignee: Petrochina Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2023-07-14

Abstract

The invention relates to a method, a device, equipment, a storage medium and application for determining lubricating oil production reaction conditions, wherein the method comprises the following steps: inputting the related information of the lubricating oil production raw materials into a pre-trained reaction product prediction model of lubricating oil hydrogenation to obtain various products under preset reaction conditions; determining physical properties of each product according to the single molecule and the content of the single molecule contained in each product; judging whether the physical properties of each product meet the preset physical property index requirements or not: if yes, calculating optimization targets of all products, and judging whether the optimization targets reach the maximum value or not: if the maximum value is reached, outputting the current reaction condition and the corresponding product parameters; if the maximum value is not reached, the current reaction condition is adjusted until the physical property of each product meets the physical property index requirement, and the optimization targets of all products reach the maximum value. The invention can accurately reflect the conversion rule of molecular components in the production process, and obviously improves the adaptability to the production operation variation of lubricating oil.

Description

Method, device, equipment, storage medium and application for determining lubricating oil production reaction condition

Technical Field

The invention relates to the technical field of petroleum processing, in particular to a method, a device, equipment, a storage medium and application for determining lubricating oil production reaction conditions.

Background

In the petroleum processing industry, in order to increase benefits brought by lubricating oil, the lubricating oil production process needs to be optimized, and at present, two optimization methods commonly adopted in the prior art comprise one for realizing the optimization in the lubricating oil production process and the other for carrying out the optimization in the lubricating oil production process through a simulation method. The optimization in the lubricating oil production process is carried out by a simulation method, usually based on a structure-oriented lumped model, and the physical property prediction of the product material is carried out based on a molecular component represented by the structure-oriented lumped method.

Disclosure of Invention

The inventors found that the first method requires a large amount of analysis and assay work, and the research efficiency is low. In the second mode, the product materials are predicted to have physical properties based on lumped components, and thus the adaptability to large adjustments in production operations is lacking. In order to solve the problems of the prior art, at least one embodiment of the present invention provides a method, an apparatus, a device, a storage medium and an application for determining a reaction condition of a lubricant production.

In a first aspect, embodiments of the present invention provide a method for determining a reaction condition for producing a lubricating oil, the method comprising:

inputting the related information of the lubricating oil production raw materials into a pre-trained product prediction model of the lubricating oil hydrogenation reaction to obtain various products under preset reaction conditions;

determining physical properties of each product according to single molecules and content of single molecules contained in each product based on a pre-trained physical property calculation model;

judging whether the physical properties of each product meet the corresponding preset physical property index requirements or not:

when the physical properties of each product meet the physical property index requirements, calculating the optimization targets of all the products, and judging whether the optimization targets reach the maximum value or not:

when the optimization target reaches the maximum value, outputting the current reaction condition and the corresponding product parameters;

when the optimization target does not reach the maximum value, the current reaction condition is adjusted, the steps are repeated according to the adjusted reaction condition, namely, the step of inputting the related information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain a plurality of products under the preset reaction condition is carried out until the physical properties of each product meet the physical property index requirement, and the optimization target of all the products reaches the maximum value.

In a possible implementation manner, the method further includes:

when the physical properties of any one product do not meet the physical property index requirements, the current reaction conditions are adjusted, and the steps are repeated according to the adjusted reaction conditions, namely, the steps of inputting the related information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain a plurality of products under the preset reaction conditions are executed.

In one possible implementation manner, the inputting the related information of the lubricant oil production raw material into a pre-trained lubricant oil hydrogenation reaction product prediction model to obtain a plurality of products under the preset reaction conditions includes:

inputting the related information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain various products under preset reaction conditions;

dividing the products into products according to any one parameter of group composition, true boiling point and distillation range to obtain the products under preset reaction conditions.

In one possible implementation, the information about the lubricant production feedstock includes a molecular composition and a processing amount of the lubricant production feedstock, wherein the molecular composition of the lubricant production feedstock includes a molecular species and a content of each molecule.

In one possible implementation, the molecular composition of the lubricating oil production feedstock is obtained by:

sampling and analyzing typical lubricating oil fractions, and pre-establishing a molecular database based on typical lubricating oil molecular components;

and acquiring the molecular composition of the lubricating oil production raw material in the molecular database according to the name of the lubricating oil production raw material.

In a possible implementation manner, the calculating the optimization objective of all products includes:

calculating optimization targets of all products according to product yields and weights of each product based on a pre-established optimization target model, wherein the optimization target model is calculated by the following expression:

T＝∑(Y _i *W _i )

wherein T is an optimization target, Y _i Product yield for the ith product, W _i Is the weight of the ith product.

In one possible implementation, the product yield is calculated by the following expression:

Y＝∑(C _j *P)

wherein Y is the product yield, C _j The content of the j-th single molecule contained in the product in all products is that P is the processing amount of the lubricating oil production raw material.

In a possible implementation, the optimization objective is at least one of cumulative benefit and objective physical property parameters.

In one possible implementation, when the optimization objective is to accumulate revenue, the weight is the price of the product.

In one possible implementation, when the optimization objective is a target physical parameter, the weight is an importance score for the product physical parameter.

In one possible implementation, the preset reaction conditions and the adjusted reaction conditions include: temperature conditions, pressure conditions, and space velocity conditions.

In one possible implementation, the lubricating oil hydrogenation reaction product prediction model is trained by the following steps:

establishing a product prediction training model of the lubricating oil hydrogenation reaction; wherein the product prediction training model comprises: a set of reaction rules and a reaction rate algorithm; the reaction rule set comprises at least one reaction rule of alkane thermal cracking, alkane catalytic cracking, aromatic hydrocarbon hydrogenation saturation and naphthene ring opening;

acquiring sample raw material information of a plurality of groups of sample raw materials;

training the reaction rule set by utilizing a plurality of groups of sample raw material information and reaction product molecular component type information to obtain a reaction rule set after training is finished;

training the reaction rate algorithm by utilizing a plurality of groups of sample raw material information, reaction product molecular component type information and content information to obtain a reaction rate algorithm after training is completed;

And determining the product prediction model according to the reaction rule set after training and the reaction rate algorithm after training.

In one possible implementation, the reaction rate constant expression of the reaction rate algorithm is the following expression:

K＝k _st ×k _absor ×Ф _cat

wherein K is a reaction rate constant, K _st For the surface reaction rate, k _absor For the adsorption rate, phi _cat Is a catalyst active factor, wherein the catalyst active factor comprises a metal center active site for hydrogenation dehydrogenation reaction and an acid center active site for carbocation reaction.

In one possible implementation, the surface reaction rate constant is obtained by the following reaction rate constant calculation formula:

wherein k is _st K is the reaction rate constant _B The method is characterized in that the method comprises the steps of taking a Boltzmann constant, h as a Planck constant, R as an ideal gas constant, T as a temperature value of an environment where a reaction path is located, exp as an exponential function based on a natural constant, deltaS as entropy change before and after reaction corresponding to a reaction rule corresponding to the reaction path, deltaE as a reaction energy barrier corresponding to the reaction rule corresponding to the reaction path, P as a pressure value of the environment where the reaction path is located, and alpha as a pressure influence factor corresponding to the reaction rule corresponding to the reaction path.

In one possible implementation, the sample raw material information of the sample raw material includes: the molecular composition of the sample material and the molecular composition of the actual product to which the sample material corresponds under specific reaction conditions.

In one possible implementation manner, the training the reaction rule set by using multiple sets of the sample raw material information and the reaction product molecular component kind information to obtain a reaction rule set after training is completed, including:

processing the molecular composition of the sample raw material according to a preset reaction rule set to obtain a reaction path corresponding to each molecule in the molecular composition of the sample raw material;

obtaining a first molecular composition of a device product according to a reaction path corresponding to each molecule in the molecular composition of the sample raw material; in the device product, comprising: the sample raw material, intermediate product and predicted product;

determining a first relative deviation according to a first molecular composition of the device product and a second molecular composition of the actual product, and judging whether the first relative deviation meets a first preset condition;

if the first relative deviation accords with a first preset condition, fixing the reaction rule set to obtain a reaction rule set after training is completed;

And if the first relative deviation does not meet the first preset condition, adjusting the reaction rules in the reaction rule set, and re-executing the steps of determining the first relative deviation and judging whether the first relative deviation meets the first preset condition according to the adjusted reaction rule set.

In one possible implementation, the determining the first relative deviation from the first molecular composition of the device product to the second molecular composition of the actual product includes:

obtaining the types of single molecules in the first molecular composition to form a first set;

obtaining the types of single molecules in the second molecular composition to form a second set;

determining whether the second set is a subset of the first set;

if the second set is not a subset of the first set, acquiring a pre-stored relative deviation value which does not meet a first preset condition as the first relative deviation value;

if the second set is a subset of the first set, a first relative deviation is calculated by a first deviation algorithm.

In a possible implementation manner, the first deviation algorithm expression is

Wherein x is ₁ For the first relative deviation, M is the first set, M ₁ M is a collection of species composition of single molecules in the molecular composition of the sample raw material ₂ And N is the second set, and the card represents the number of elements in the set.

In one possible implementation manner, the training the reaction rate algorithm by using multiple sets of the sample raw material information and the reaction product molecular component type and content information to obtain a reaction rate algorithm after training, including:

according to the reaction rate algorithm, respectively calculating the reaction rate of a reaction path corresponding to each molecule in the molecular composition of the sample raw material;

obtaining the predicted content of each molecule in a predicted product corresponding to the sample raw material according to the molecular content of each molecule in the sample raw material and the reaction rate corresponding to the reaction path of the molecule;

calculating a second relative deviation according to the predicted content of each molecule in the predicted product and the actual content of each molecule in the actual product, and judging whether the second relative deviation meets a second preset condition or not;

if the second relative deviation accords with a second preset condition, fixing the reaction rate algorithm to obtain a reaction rate algorithm after training is finished;

And if the second relative deviation does not meet the second preset condition, adjusting parameters in the reaction rate algorithm, and re-executing the steps of calculating the second relative deviation and judging whether the second relative deviation meets the second preset condition according to the adjusted reaction rate algorithm.

In one possible implementation, the determining the physical properties of each product according to the single molecule and the content of the single molecule contained in each product based on the physical property calculation model trained in advance includes:

calculating to obtain each single molecule physical property of each single molecule based on a physical property calculation model trained in advance;

according to the preset mixing rule of the physical properties of each product, calculating the physical properties of each product through the physical properties and the content of each single molecule.

In one possible implementation manner, the calculating, based on a physical property calculation model trained in advance, each single molecule physical property of each single molecule includes:

inputting the number of groups of each group constituting the single molecule and the contribution value of each group to physical properties into a pre-trained physical property calculation model;

and obtaining physical properties of the single molecule output by the physical property calculation model.

In one possible implementation, before calculating each single molecule physical property based on a physical property calculation model trained in advance, the method further includes:

comparing the number of groups constituting each group of the single molecule with the molecular information of template single molecules with known physical properties prestored in a database; the molecular information includes: the number of groups of each group constituting the template single molecule;

judging whether the template single molecule which is the same as the single molecule exists or not;

outputting physical properties of the template single molecule as physical properties of the single molecule if the template single molecule identical to the single molecule exists;

and a step of executing the step of inputting a pre-trained physical property calculation model by the number of groups of each group constituting the single molecule and the contribution value of each group to physical properties if the template single molecule identical to the single molecule does not exist.

In one possible implementation, the physical property index is at least one of viscosity, viscosity index, pour point, aniline point.

In a second aspect, embodiments of the present invention provide a lubricating oil production optimizing apparatus, the apparatus comprising:

An input unit for inputting information about the lubricating oil production raw material into a pre-trained product prediction model of the lubricating oil hydrogenation reaction to obtain a plurality of products under preset reaction conditions or adjusted reaction conditions;

a determination unit for determining physical properties of each product from single molecules contained in each product and contents of single molecules based on a physical property calculation model trained in advance;

the processing unit is used for judging whether the physical properties of each product meet the corresponding preset physical property index requirements or not: when the physical properties of each product meet the physical property index requirements, calculating the optimization targets of all the products, and judging whether the optimization targets reach the maximum value or not: when the optimization target reaches the maximum value, outputting the current reaction condition and the corresponding product parameters; and when the optimization target does not reach the maximum value, adjusting the current reaction condition to obtain the adjusted reaction condition.

In a third aspect, embodiments of the present invention provide an application of the above-described method for determining reaction conditions for producing a lubricating oil in a method for producing a lubricating oil.

In a fourth aspect, embodiments of the present invention provide a process for producing a lubricant, using the reaction conditions determined by the above-described determination method for reaction conditions for producing a lubricant.

In a fifth aspect, an embodiment of the present invention provides a lubrication oil production reaction condition determining apparatus, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the steps of the lubricating oil production reaction condition determining method when executing the program stored in the memory.

In a sixth aspect, embodiments of the present invention provide a computer-readable storage medium storing one or more programs executable by one or more processors to implement the steps of the above-described method for determining a lubricating oil production reaction condition.

Compared with the prior art, the technical scheme of the invention has the following advantages: according to the embodiment of the invention, the related information of the lubricating oil production raw materials is input into a pre-trained product prediction model of the lubricating oil hydrogenation reaction, so that various products under preset reaction conditions are obtained; determining physical properties of each product according to single molecules and content of single molecules contained in each product based on a pre-trained physical property calculation model; judging whether the physical properties of each product meet the physical property index requirements: if yes, calculating optimization targets of all products, and judging whether the optimization targets reach the maximum value or not: if the maximum value is reached, outputting the current reaction condition and the corresponding product parameters; if the maximum value is not reached, the current reaction condition is regulated, and the relevant information of the lubricating oil production raw materials is input into a pre-trained product prediction model according to the regulated reaction condition, so that a plurality of products under the preset reaction condition are obtained, until the physical properties of each product meet the physical property index requirement, and the optimization targets of all products reach the maximum value.

Drawings

FIG. 1 is a schematic flow chart of a method for determining reaction conditions in the production of lubricating oil according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a method for determining reaction conditions for producing lubricating oil according to another embodiment of the present invention;

FIG. 3 is a schematic flow chart of a method for determining reaction conditions for producing lubricating oil according to another embodiment of the present invention;

FIG. 4 is a schematic diagram of a device for determining the reaction conditions in the production of lubricating oil according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a lubricating oil production reaction condition determining apparatus according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

As shown in FIG. 1, the embodiment of the invention provides a method for determining the reaction conditions of lubricating oil production. Referring to fig. 1, the method for determining the reaction conditions for the production of lubricating oil comprises:

S11, inputting relevant information of a lubricating oil production raw material into a pre-trained product prediction model of a lubricating oil hydrogenation reaction to obtain various products under preset reaction conditions;

in the present embodiment, the information about the lubricating oil production raw material includes the molecular composition and the processing amount of the lubricating oil production raw material, wherein the molecular composition of the lubricating oil production raw material includes the molecular species and the content of each molecule.

In this embodiment, the preset reaction conditions include: temperature, pressure and space velocity, wherein space velocity refers to the amount of gas treated by a unit volume of catalyst per unit time under specified conditions including temperature and pressure conditions, and the unit is m 3/(m 3 catalyst.h), and can be simplified to h-1.

In the embodiment of the invention, the product prediction model is used for predicting the product of the catalytic hydrogenation reaction of the lubricating oil production raw material at the molecular level under the preset reaction condition, and the product prediction model can also be called a molecular level lubricating oil processing device model, a lubricating oil hydrogenation model or a lubricating oil production process reaction mechanism model. The reaction processes implemented in the product prediction model include, but are not limited to, the following chemical reactions: the method comprises the steps of finishing reaction, hydrotreating reaction, catalytic dewaxing reaction, isomerization dewaxing reaction, alkane thermal cracking reaction, alkane catalytic cracking reaction, aromatic hydrocarbon hydrogenation saturation reaction and cycloparaffin ring opening reaction, wherein each chemical reaction has a corresponding reaction rule. The reaction rules corresponding to each chemical reaction can be rules of chemical reactions simulated by each molecule in the product prediction model, each reaction rule is obtained by induction and finishing in advance according to different reaction mechanisms, the reaction rules represent reaction processes of the corresponding chemical reactions under the conditions of preset temperature, pressure, airspeed and catalyst, so that the actual production process of the lubricating oil production raw material is simulated, and because the molecular composition of the lubricating oil production raw material is complex, the reaction paths of all molecules can be quickly generated based on the reaction rules, and the simulation calculation is performed in the model, so that the product of the lubricating oil hydrogenation reaction is obtained.

S12, determining physical properties of each product according to single molecules and the content of the single molecules contained in each product based on a pre-trained physical property calculation model;

s13, judging whether the physical properties of each product meet the corresponding preset physical property index requirements or not:

if yes, go to step S14;

if not, executing step S17;

in this embodiment, the predetermined physical property index is at least one of viscosity, viscosity index, pour point, and aniline point. The physical property index requirements of different products are different.

S14, calculating optimization targets of all products;

in this embodiment, the calculating the optimization objectives for all products includes:

T＝∑(Y _i *W _i )

The product yield is obtained from the output of the lube oil hydrogenation reaction product prediction model and is calculated by the following expression:

Y＝∑(C _j *P)

In this embodiment, the optimization objective is at least one of accumulated revenue and a target physical property parameter, where when the optimization objective is accumulated revenue, the weight is a product price; when the optimization target is a target physical parameter, the weight is an importance score of the physical parameter of the product.

S15, judging whether the optimization target reaches the maximum value or not:

if yes, go to step S16;

if not, executing step S17;

in this embodiment, whether the optimization target reaches the maximum value may be determined by a global optimization algorithm of multi-start point random search, or the optimization algorithm further includes: optimization algorithms such as gradient descent algorithm, newton method, conjugate gradient method and heuristic optimization method, wherein the gradient descent algorithm comprises the following steps: the random gradient descent algorithm or the batch gradient descent algorithm can determine that the optimization targets of all products reach the maximum value through the method. For specific implementation manner, reference may be made to the detailed description of the above optimization algorithm in the prior art, which is not repeated here.

S16, outputting the current reaction condition and corresponding product parameters;

in this embodiment, the product parameters corresponding to the current reaction conditions are parameters such as molecular composition, yield, and yield of the lubricant product under the current reaction conditions, and the output current reaction conditions and corresponding product parameters can be applied to actual lubricant production to provide references for the actual lubricant production process.

S17, adjusting the current reaction conditions, and repeating the steps according to the adjusted reaction conditions, namely, executing the step of inputting the related information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain a plurality of products under the current reaction conditions until the physical properties of each product meet the physical property index requirements, and the optimization targets of all the products reach the maximum value.

In one embodiment, the molecular composition of the lubricating oil production feedstock is obtained by:

sampling and analyzing typical lubricating oil fractions based on a structure-oriented lumped (Structure Oriented Lump, SOL) method, and pre-establishing a molecular database based on typical lubricating oil molecular components;

according to the names of the lubricating oil production raw materials, the molecular composition of the lubricating oil production raw materials is obtained in the molecular database.

The typical lubricating oil fraction is suitable for the hydrogenation reaction of lubricating oil, is a product after petroleum processing, and can be used as a lubricating oil production raw material. For example, the lubricating oil product obtained by the petroleum raw material through the atmospheric and vacuum device can also be a product output by a catalytic reforming device, or a product output after catalytic hydrofining or catalytic hydro-upgrading, or a product obtained by processing crude oil or other oil products for multiple times by other petroleum processing devices. In this embodiment, the SOL method is a method for representing molecules by using a SOL molecule characterization method, which means that 24 structure increment segments are used to characterize the basic structure of a complex hydrocarbon molecule. Any petroleum molecule can be expressed in terms of a specific set of structurally incremental fragments. The 24 structural increment fragments in the SOL molecule characterization method are 24 groups, the groups are a part of characteristic structures of the molecules, and each group generally performs chemical reaction as a whole. The SOL molecular characterization method belongs to the lumped on the molecular scale, reduces the number of molecules in an actual system from millions to thousands, and greatly reduces the simulation complexity. The characterization method can represent not only alkanes, cycloalkanes, up to complex aromatic structures containing 50-60 carbon atoms, but also olefins or cycloalkenes as intermediate products or secondary reaction products, and further consider heteroatom compounds containing sulfur, nitrogen, oxygen, etc. The molecular structure may be determined by one or more of raman spectroscopy, quaternary rod gas chromatography-mass spectrometer detection, gas chromatography/field ionization-time of flight mass spectrometry, gas chromatography, near infrared spectroscopy, sensor methods, nuclear magnetic resonance spectroscopy, and then the single molecule may be represented by structure-directed lumped molecular characterization methods.

For each typical lube fraction, the true single molecule composition of the typical lube fraction is determined by sampling analysis, and each single molecule is represented by the SOL method, resulting in a molecular composition characterized by the SOL method for the typical lube fraction, i.e., a molecular database based on the typical lube molecule composition is built. The molecular database includes names and molecular compositions of typical lubricating oils.

In some embodiments, as shown in fig. 2, in step S11, the inputting the information about the lubricant production raw material into a pre-trained lubricant hydrogenation reaction product prediction model, to obtain a plurality of products under the preset reaction conditions, includes:

s21, inputting relevant information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain various products under preset reaction conditions;

s22, dividing the products into products according to any one of parameters of group composition, true boiling point and distillation range to obtain the products under preset reaction conditions.

In some embodiments, as shown in fig. 3, in step S11, the lubricating oil hydrogenation reaction product prediction model is trained by:

S31, establishing a product prediction training model of the lubricating oil hydrogenation reaction; wherein the product prediction training model comprises: a set of reaction rules and a reaction rate algorithm; the reaction rule set comprises at least one reaction rule of a complementary refining reaction, a hydrotreating reaction, a catalytic dewaxing reaction, an isomerization dewaxing reaction, an alkane thermal cracking reaction, an alkane catalytic cracking reaction, an aromatic hydrocarbon hydrogenation saturation reaction and a cycloalkane ring-opening reaction; the reaction rules in the reaction rule set are rules of chemical reactions simulated by each molecule in the product prediction model, each reaction rule is obtained by induction and finishing in advance according to different reaction mechanisms, the reaction rules represent reaction processes of the corresponding chemical reactions under the preset temperature, pressure, airspeed and catalyst conditions, so that the actual production process of the lubricating oil production raw materials is simulated, and because the molecular composition of the lubricating oil production raw materials is complex, the reaction path of each molecule can be quickly generated based on the reaction rules, and the simulation calculation is performed in the model, so that the product of the lubricating oil hydrogenation reaction is obtained.

S32, acquiring sample raw material information of a plurality of groups of sample raw materials; wherein the sample raw material information of the sample raw material includes: the molecular composition of the sample raw material and the molecular composition of the corresponding actual product of the sample raw material under specific reaction conditions;

S33, training the reaction rule set by utilizing a plurality of groups of sample raw material information and reaction product molecular component type information to obtain a reaction rule set after training is finished;

s34, training the reaction rate algorithm by utilizing a plurality of groups of sample raw material information and reaction product molecular component type information and content information to obtain a reaction rate algorithm after training is completed;

and S35, determining the product prediction model according to the reaction rule set after training and the reaction rate algorithm after training.

In some embodiments, in step S31, the expression of the reaction rate constant of the reaction rate algorithm is the following expression:

K＝k _st ×k _absor ×Ф _cat

wherein K is a reaction rate constant, K _st Is the surface reaction rate constant, k _absor For the adsorption rate constant, phi _cat Is a catalyst active factor, wherein the catalyst active factor at least comprises a metal center active site for hydrogenation dehydrogenation reaction and an acid center active site for carbonium ion reaction according to different active sites.

In this example, each reaction rate constant in the above formula, also called a rate constant, is a quantitative expression of chemical reaction rate, and its physical meaning is that its value corresponds to the reaction rate when all the substances participating in the reaction are at a unit concentration (1 mol·l), so is also called a specific rate of the reaction. The different reactions have different reaction rate constants, which are related to reaction temperature, solid surface properties, reaction medium (solvent), catalyst, etc., and even vary with the shape and properties of the reactor, but are independent of concentration.

Wherein the surface reaction rate constant K _st According to the following calculation formula:

wherein K is _st Is the surface reaction rate constant, k _B Is glassThe method comprises the steps of setting a reaction path, setting a reaction energy barrier corresponding to a reaction rule corresponding to the reaction path, setting a temperature value of the environment where the reaction path is located, setting an ideal gas constant, setting an exp as an exponential function based on a natural constant, setting deltaS as an entropy change before and after the reaction corresponding to the reaction rule corresponding to the reaction path, setting deltaE as a reaction energy barrier corresponding to the reaction rule corresponding to the reaction path, setting P as a pressure value of the environment where the reaction path is located, and setting alpha as a pressure influence factor corresponding to the reaction rule corresponding to the reaction path.

In the present embodiment, the catalyst activity factor Φ _cat The competitive adsorption capacity of the reactant molecules at different active sites of the catalyst is characterized. The active sites of the lubricating oil hydrogenation catalyst mainly comprise metal centers for hydrogenation and dehydrogenation reactions, desulfurated active sites of the catalyst and acid centers of the catalyst for carbonium ion reactions. Different active sites react differently, and molecules of the same type have the same catalyst active factor phi at the same active site _cat The acquisition may be by software simulation or querying device production data, as detailed in the prior art.

In some embodiments, in step S33, training the reaction rule set by using multiple sets of the sample raw material information and the reaction product molecular component kind information to obtain a reaction rule set after training, including:

if the first relative deviation does not meet the first preset condition, adjusting the reaction rule in the reaction rule set, and re-executing the steps of determining the first relative deviation and judging whether the first relative deviation meets the first preset condition according to the adjusted reaction rule set, namely processing the molecular composition of the sample raw material according to the adjusted reaction rule set to obtain the first molecular composition of the adjusted device product; and re-determining a first relative deviation according to the adjusted first molecular composition of the device product and the adjusted second molecular composition of the actual product until the first relative deviation meets a first preset condition.

In the embodiment of the invention, the first preset condition is a preset relative deviation range of the first molecular composition of the device product and the second molecular composition of the actual product. The two end values of the preset relative deviation range are empirical values or experimentally obtained values, and the specific determination process may refer to the detailed description in the prior art, and will not be described herein.

Further, determining a first relative deviation from a first molecular composition of the device product and a second molecular composition of the actual product, comprising:

determining whether the second set is a subset of the first set;

if the second set is a subset of the first set, calculating a first relative deviation by the following calculation formula:

In some embodiments, in step S34, the training is performed on the reaction rate algorithm by using a plurality of sets of the sample raw material information and the reaction product molecular component type and content information, to obtain a reaction rate algorithm after training is completed, including:

If the second relative deviation does not meet the second preset condition, adjusting parameters in the reaction rate algorithm, and re-executing the steps of calculating the second relative deviation and judging whether the second relative deviation meets the second preset condition according to the adjusted reaction rate algorithm, namely calculating the reaction rate of a reaction path corresponding to each molecule in the molecular composition of the sample raw material according to the adjusted reaction rate algorithm to obtain the predicted content of each molecule in the adjusted predicted product; and re-calculating a second relative deviation according to the predicted content of each molecule in the adjusted predicted product and the actual content of each molecule in the actual product until the second relative deviation meets a second preset condition.

In the embodiment of the present invention, the second preset condition is a preset relative deviation range between the predicted content of each molecule in the predicted product and the actual content of each molecule in the actual product. The two end values of the preset relative deviation range are empirical values or experimentally obtained values, and the specific determination process may refer to the detailed description in the prior art, and will not be described herein.

In some embodiments, in step S12, the determining the physical properties of each product according to the single molecule and the content of the single molecule contained in each product based on the physical property calculation model trained in advance includes:

In this embodiment, the physical property calculation model trained in advance is a model constructed by characterizing single molecules in a molecular composition based on a structure-oriented lumped (Structure Oriented Lump, SOL) molecular characterization method. The physical property calculation model constructed based on the SOL molecular characterization method may include physical property calculation models for calculating density, viscosity, pour point, aniline point, respectively. In addition, the physical property calculation model can improve calculation precision along with the increase of training data, can be updated continuously, and is convenient for later maintenance.

In the embodiment of the invention, the preset mixing rule is a mixing rule set according to the physical properties of the predicted lubricating oil product, and the preset mixing rule corresponds to the types and the amounts of the used lubricating oil blending raw materials, and the corresponding lubricating oil product is obtained by mixing different lubricating oil blending raw materials.

In some embodiments, calculating the individual single molecule physical properties of each of the single molecules based on a pre-trained physical property calculation model comprises:

Inputting the number of groups of each group constituting the single molecule and the contribution value of each group to physical properties into a physical property calculation model trained in advance, and obtaining the physical properties of the single molecule output by the physical property calculation model.

Wherein the contribution value of each group of the single molecule to the physical property is the contribution value of each group to the physical property obtained by training when the physical property calculation model is obtained by training, and the contribution value is stored in a preset storage position and then obtained from the preset storage position.

In some embodiments, in order to quickly obtain the properties of each single molecule, before calculating the properties of each single molecule based on a pre-trained property calculation model, the method further includes:

And if the template single molecule which is the same as the single molecule does not exist, performing the steps of inputting the number of groups of each group which form the single molecule and the contribution value of each group to physical properties into a pre-trained physical property calculation model.

In some embodiments, the step of training the physical property calculation model comprises:

constructing a single-molecule physical property calculation training model, wherein the physical property calculation training model is as follows:

wherein f is the physical property of the sample single molecule, n _i The number of groups, Δf, being the i-th group _i Is the ith group pairA is a correlation constant;

obtaining the number of groups of each group constituting a single molecule of the sample; the physical properties of the sample single molecule are known;

inputting the number of groups of each group contained in the sample single molecule into the physical property calculation model;

obtaining the predicted physical property of the sample single molecule output by the physical property calculation training model;

if the deviation value between the predicted physical property and the known physical property of the sample single molecule is smaller than a preset deviation threshold value, judging that the physical property calculation training model converges, taking the converged physical property calculation training model as a physical property calculation model, acquiring a contribution value corresponding to each group in the converged physical property calculation training model, and storing the contribution value as a contribution value of the group to the physical property;

And if the deviation value between the predicted physical property and the known physical property is greater than or equal to the deviation threshold value, adjusting the contribution value corresponding to each group in the physical property calculation training model, and re-executing the model training until the physical property calculation model converges.

In this embodiment, a training sample set is set in advance. A plurality of sample single molecule information is included in the training sample set. Sample single molecule information including, but not limited to: the number of groups of each group constituting a sample single molecule, and the physical properties of the sample single molecule.

In this embodiment, when the physical property calculation model is obtained, the contribution value of each group to each physical property is stored for each group, so that when the physical property of a single molecule is calculated later, the contribution value of each group in the single molecule to the physical property to be obtained can be obtained, the number of groups of each group of the single molecule and the contribution value of each group to the physical property to be obtained are used as the input of the physical property calculation model, the physical property calculation model uses the number of groups of each group of the single molecule as a model variable, and the contribution value of each group to the physical property to be obtained is used as a model parameter (the adjustable contribution value of each group to the physical property in the alternative physical property calculation training model).

In this embodiment, if there are a plurality of physical properties of the sample single molecules, the predicted physical properties of the sample single molecules outputted from the physical property calculation training model are also a plurality, and at this time, deviation values between each predicted physical property and the corresponding known physical property are calculated, whether the deviation values between all the predicted physical properties and the corresponding known physical properties are smaller than the preset deviation values is determined, if yes, the physical property calculation model is determined to converge, and the contribution value of each physical property corresponding to each group can be obtained from the converged physical property calculation model, and by the above-described scheme, the contribution value of each group to different physical properties can be obtained.

In some embodiments, the method further comprises: and updating the physical property calculation model. That is, after the physical property calculation model is obtained, the number of groups of each group of the new sample single molecule and the corresponding initial contribution value are newly input into the model, and the model training is performed, so that the physical property calculation model is updated.

In some embodiments, the obtaining the number of groups of each group comprising a single molecule of the sample comprises:

determining the number of each level of groups and corresponding groups in all groups of the single molecule of the sample; wherein:

All groups constituting a single molecule are taken as primary groups;

m groups which are simultaneously present and contribute to the same physical property are taken as M-class groups, and the number of the M groups is taken as the class of the M-class groups;

all groups of the sample single molecule comprise a primary group, a secondary group, a … … and an N-level group, wherein N is more than or equal to M, and M is a positive integer more than or equal to 2.

In one embodiment, based on the determined groups of each stage and the number of groups corresponding to each stage in all groups of the sample single molecule, a physical property calculation training model is established as follows:

wherein f is the physical property of the sample single molecule, m _1i The number of groups, Δf, being the i-th group in the primary groups _1i Is the contribution value of the ith group in the primary groups to physical properties, m _2j The number of groups, Δf, being the j-th group in the secondary groups _2j The contribution value of the j-th group in the secondary groups to physical properties; m is m _Nl The number of groups, Δf, being the first group in the N-stage groups _Nl The contribution value of the first group in the N-level groups to physical properties; a is a correlation constant; n is a positive integer greater than or equal to 2.

In the embodiment of the present invention, a plurality of groups that act together with one physical property may be used as the multi-stage groups, and specifically, for example, when N6 and N4 groups are present in different molecules separately, they have a certain influence on the physical property, and when they are present in one molecule, they have a certain fluctuation in the contribution value to the physical property on the basis of the original contribution value to the physical property. The multi-level groups can be divided by molecular bond force among the groups, the groups are divided into a plurality of different levels according to a preset bond force interval, and the levels of the groups can be specifically divided according to the influence of molecular stability on physical properties due to different molecular bond force and different influence on different physical properties.

For example: for boiling point, 24 groups are all primary groups in SOL-based molecular characterization methods; of the 24 groups, one or more of the groups such as N6, N5, N4, N3, me, AA, NN, RN, NO, RO and KO can contribute to boiling point, and the contribution values of the groups to the physical property are inconsistent for different physical properties, but the contribution values of the same group to the same physical property in different molecules are consistent.

The physical properties of the product can be calculated after the physical properties of each single molecule of the product are obtained based on the single molecule physical property calculation model.

For example, when the physical property of the product is calculated as density, according to the preset mixing rule of the physical property of each product, the following calculation formula is established, and the density of the product of the lubricating oil hydrogenation device can be calculated according to the physical properties and the content of each single molecule:

density＝∑(D _i ×x _i _volume)；

Wherein density is the density of the mixture, D _i For the density of the ith single molecule, xi_volume is the content of the ith single molecule.

The density of each single molecule of each product can be obtained through the following pre-trained density calculation model, the group number of each group of the single molecule of the molecular composition data of the product and the contribution value of each group to physical properties can be input into the density calculation model, and the density of the single molecule can be obtained through calculation:

wherein D is the density of the single molecule, SOL is a single molecule vector converted from the number of GROUPs of each GROUP constituting the single molecule, GROUP ₂₁ GROUP is the n+1-th contribution vector obtained by converting the contribution of the primary GROUP to the density ₂₂ GROUP is an n+2-th contribution vector obtained by converting the contribution of the secondary GROUP to the density _2N The 2N contribution value vector is obtained by converting the contribution value of the N-level group to the density, and e is a fourth preset constant; and N is a positive integer greater than or equal to 2.

The above-mentioned single molecule vector converted from the number of groups of each group constituting a single molecule includes: taking the number of all groups constituting a single molecule as the dimension of a single molecule vector; the number of groups of each group is taken as the element value of the corresponding dimension in the single-molecule vector.

According to the n+1 contribution value vector obtained by converting the contribution value of each primary group of single molecule to the density, the method comprises the following steps: taking the number of primary groups as the dimension of the N+1 contribution value vector; and taking the contribution value of each primary group to the density as the element value of the corresponding dimension in the N+1th contribution value vector. An n+2-th contribution value vector obtained by converting the contribution value of each secondary group of single molecules to the density comprises: taking the number of the secondary groups as the dimension of the N+2 contribution value vector; and taking the contribution value of each secondary group to the density as the element value of the corresponding dimension in the N+2 contribution value vector. In this way, the 2N-th contribution value vector obtained by converting the contribution value of each N-level group of a single molecule to the density comprises: taking the number of N-level groups as the dimension of the 2N contribution value vector; and taking the contribution value of each N-level group to the density as the element value of the corresponding dimension in the 2N-th contribution value vector.

In some embodiments, when the physical property of the product is a pour point, calculating the physical property of the product comprises:

calculating the pour point contribution value of each single molecule according to the density and the molecular weight of each single molecule;

the pour point of the mixture was calculated from the pour point contribution and content of all single molecules in the mixture.

In the embodiment of the invention, the calculation can be performed based on a calculation formula in the prior art. In the embodiment of the present invention, the calculation process of the pour point contribution value may refer to a specific implementation manner in the prior art, and may adopt a calculation formula disclosed in the prior art to calculate the pour point of the mixture according to the pour point contribution values and the content of all single molecules in the mixture, and the specific implementation process may not be specifically limited herein.

In some embodiments, when the physical property of the product is an aniline point, calculating the physical property of the product comprises:

calculating to obtain the aniline point of the single molecule according to the density and boiling point of the single molecule;

the aniline point of the mixture was calculated from the aniline point and the content of all single molecules in the mixture.

In the embodiment of the invention, the calculation can be performed based on a calculation formula in the prior art. In the embodiment of the invention, the calculation process of the aniline point contribution value can refer to a specific implementation mode in the prior art, and a calculation formula disclosed in the prior art can be adopted to calculate the aniline point of the mixture according to the aniline point contribution values and the content of all single molecules in the mixture, and the specific implementation process is not particularly limited.

According to the method for determining the reaction conditions of the production of the lubricating oil, the reaction mechanism model of the production process of the lubricating oil is established on the basis of molecular components, the physical properties of the product materials are predicted on the basis of molecular components, the conversion rule of the molecular components in the production process is accurately reflected, the adaptability of the reaction mechanism model of the production process of the lubricating oil to operation variation is remarkably improved, and the problem of operation optimization of a lubricating oil production device is better solved.

The method for determining the reaction conditions of lubricating oil production fully excavates the synergy potential of the raw materials and the processing device by optimizing the reaction conditions, improves the yield of target products and realizes the maximization of product benefits.

Based on the same inventive concept, as shown in fig. 4, an embodiment of the present invention provides a lubricating oil production reaction condition determining apparatus, the apparatus comprising: an input unit 11, a determination unit 12 and a processing unit 13.

In the present embodiment, an input unit 11 for inputting information about a lubricant production raw material into a pre-trained product prediction model of a lubricant hydrogenation reaction to obtain a plurality of products under preset reaction conditions or adjusted reaction conditions;

in the present embodiment, a determination unit 12 for determining physical properties of each product from single molecules and the content of single molecules contained in each product based on a physical property calculation model trained in advance;

In this embodiment, the processing unit 13 is configured to determine whether the physical properties of each product meet the corresponding preset physical property index requirements: when the physical properties of each product meet the physical property index requirements, calculating the optimization targets of all the products, and judging whether the optimization targets reach the maximum value or not: when the optimization target reaches the maximum value, outputting the current reaction condition and the corresponding product parameters; and when the optimization target does not reach the maximum value, adjusting the current reaction condition to obtain the adjusted reaction condition.

In some embodiments, the processing unit 13 is further configured to adjust the current reaction condition to obtain the adjusted reaction condition when the physical properties of any one of the products do not meet the physical property index requirement.

In some embodiments, the input unit 11 is further configured to: inputting the related information of the lubricating oil production raw materials into a pre-trained lubricating oil hydrogenation reaction product prediction model to obtain various products under preset reaction conditions;

In some embodiments, in the input unit 11, the information about the lubricating oil production raw material includes a molecular composition and a processing amount of the lubricating oil production raw material, wherein the molecular composition of the lubricating oil production raw material includes a molecular species and a content of each molecule.

In some embodiments, the molecular composition is obtained in the input unit 11 by:

In some embodiments, the processing unit 13 is further configured to:

T＝∑(Y _i *W _i )

In some embodiments, in the processing unit 13, the product yield is calculated by the following expression:

Y＝∑(C _j *P)

In some embodiments, in the processing unit 13, the optimization objective is at least one of a cumulative benefit and a target physical property parameter, wherein when the optimization objective is a cumulative benefit, the weight is a product price; when the optimization target is a target physical parameter, the weight is an importance score of the physical parameter of the product.

In some embodiments, in the input unit 11, the preset reaction conditions and the adjusted reaction conditions include: temperature conditions, pressure conditions, and space velocity conditions.

In some embodiments, the input unit 11 is further configured to:

In some embodiments, in the input unit 11, the expression of the reaction rate constant of the reaction rate algorithm is the following expression:

K＝k _st ×k _absor ×Ф _cat

Wherein K is a reaction rate constant, K _st For the surface reaction rate, k _absor For the adsorption rate, phi _cat Is a catalyst active factor, wherein the catalyst active factor at least comprises a metal center active site for hydrogenation dehydrogenation reaction and an acid center active site for carbonium ion reaction according to different active sites.

In some embodiments, the surface reaction rate constant k is obtained in the input unit 11 by the following reaction rate constant calculation formula _st ：

In some embodiments, in the input unit 11, sample raw material information of the sample raw material includes: the molecular composition of the sample material and the molecular composition of the actual product to which the sample material corresponds under specific reaction conditions.

In some embodiments, the input unit 11 is specifically configured to:

determining whether the second set is a subset of the first set;

In some embodiments, in the input unit 11, the first deviation algorithm expression is

Wherein x is ₁ For the first relative deviation, M is the first set, M ₁ Group of species of single molecule in molecular composition of the sample raw materialSet of components, M ₂ And N is the second set, and the card represents the number of elements in the set.

In some embodiments, the input unit 11 is specifically configured to:

In some embodiments, the determining unit 12 is further configured to:

In some embodiments, the determining unit 12 is specifically configured to:

In some embodiments, the determining unit 12 is specifically configured to: comparing the number of groups constituting each group of the single molecule with the molecular information of template single molecules with known physical properties prestored in a database; the molecular information includes: the number of groups of each group constituting the template single molecule;

In some embodiments, in the processing unit 13, the physical property index is at least one of viscosity, viscosity index, pour point, aniline point.

The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.

For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present invention. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

Based on the same inventive concept, the embodiment of the invention also provides an application of the method for determining the reaction conditions of lubricating oil production in the lubricating oil production method.

Based on the same inventive concept, the embodiment of the invention also provides a lubricating oil production process method, which uses the reaction conditions determined by the lubricating oil production reaction condition determining method.

Based on the same inventive concept, as shown in fig. 5, an embodiment of the present invention provides a lubrication oil production reaction condition determining apparatus, which includes a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 complete communication with each other through the communication bus 1140;

a memory 1130 for storing a computer program;

processor 1110, when executing the program stored in memory 1130, implements the following lubricant production reaction condition determination method:

And when the optimization target does not reach the maximum value, adjusting the current reaction condition, and repeating the steps according to the adjusted reaction condition.

The communication bus 1140 may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The communication bus 1140 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface 1120 is used for communication between the electronic device and other devices described above.

The memory 1130 may include random access memory (Random Access Memory, simply RAM) or may include non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. Optionally, the memory 1130 may also be at least one storage device located remotely from the processor 1110.

The processor 1110 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium storing one or more programs executable by one or more processors to implement the steps of the lubricating oil production reaction condition determining method in any of the possible implementations described above.

Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

Based on the same inventive concept, embodiments of the present invention also provide a computer program product comprising a computer program which when executed by a processor realizes the steps of the lubricating oil production reaction condition determining method in any of the possible implementations described above.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, server, or data center. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc., that contain an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining reaction conditions for the production of a lubricating oil, said method comprising:

2. The method according to claim 1, wherein the method further comprises:

when the physical properties of any one product do not meet the physical property index requirements, the current reaction conditions are adjusted, and the steps are repeated according to the adjusted reaction conditions.

3. The method of claim 1, wherein inputting the information about the lubricant production feedstock into a pre-trained lubricant hydrogenation reaction product prediction model to obtain a plurality of products under the predetermined reaction conditions comprises:

4. A method according to any one of claims 1-3, wherein the information about the lubricant production stock comprises the molecular composition and processing amount of the lubricant production stock, wherein the molecular composition of the lubricant production stock comprises the molecular species and the content of each molecule.

5. The method of claim 4, wherein the molecular composition of the lubricant production feedstock is obtained by:

6. A method according to any one of claims 1-3, wherein said calculating an optimization objective for all products comprises:

T＝∑(Y _i *W _i )

7. The method of claim 6, wherein the product yield is calculated by the expression:

Y＝∑(C _j *P)

8. The method of claim 7, wherein the optimization objective is at least one of cumulative benefit and objective physical property parameters;

When the optimization target is accumulated income, the weight is the price of the product;

when the optimization target is a target physical parameter, the weight is an importance score of the physical parameter of the product.

9. A method according to any one of claims 1-3, wherein the preset reaction conditions and the adjusted reaction conditions comprise: temperature conditions, pressure conditions, and space velocity conditions.

10. A method according to any one of claims 1-3, wherein the lube oil hydrogenation reaction product predictive model is trained by:

11. The method of claim 10, wherein the reaction rate constant expression of the reaction rate algorithm is:

K＝k _st ×k _absor ×Ф _cat

wherein K is a reaction rate constant, K _st Is the surface reaction rate is constantNumber k _absor For the adsorption rate constant, phi _cat Is a catalyst active factor, wherein the catalyst active factor comprises a metal center active site for hydrogenation dehydrogenation reaction and an acid center active site for carbocation reaction.

12. The method according to claim 11, comprising:

the surface reaction rate constant is obtained by the following reaction rate constant calculation formula:

13. The method of claim 10, wherein the sample feedstock information for the sample feedstock comprises: the molecular composition of the sample material and the molecular composition of the actual product to which the sample material corresponds under specific reaction conditions.

14. The method of claim 10, wherein training the reaction rule set using the plurality of sets of sample raw material information and reaction product molecular component type information to obtain a trained reaction rule set comprises:

15. The method of claim 14, wherein determining the first relative deviation from the first molecular composition of the device product and the second molecular composition of the actual product comprises:

determining whether the second set is a subset of the first set;

16. The method of claim 15, wherein the first bias algorithm expression is

17. The method of claim 10, wherein training the reaction rate algorithm using the plurality of sets of sample raw material information and reaction product molecular component type and content information to obtain a trained reaction rate algorithm comprises:

18. A method according to any one of claims 1-3, wherein determining the physical properties of each product from the single molecule and the content of single molecules contained in each product based on a pre-trained physical property calculation model comprises:

19. The method of claim 18, wherein calculating individual single molecule physical properties for each of the single molecules based on a pre-trained physical property calculation model comprises:

20. The method of claim 19, further comprising, prior to calculating each of the single molecule physical properties for each of the single molecules based on a pre-trained physical property calculation model:

21. A method according to any one of claims 1-3, wherein the predetermined physical property index is at least one of viscosity, viscosity index, pour point, aniline point.

22. A lubricating oil production reaction condition determining apparatus, characterized by comprising:

23. Use of the lubricating oil production reaction condition determining method according to any one of claims 1 to 21 in a lubricating oil production process.

24. A process for producing a lubricating oil, characterized by using the reaction conditions determined by the lubricating oil production reaction condition determining method according to any one of claims 1 to 21.

25. The lubricating oil production reaction condition determining device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the steps of the method for determining a lubricating oil production reaction condition according to any one of claims 1 to 21 when executing a program stored on a memory.

26. A computer-readable storage medium storing one or more programs executable by one or more processors to implement the steps of the lubricating oil production reaction condition determining method of any one of claims 1-21.