Production process of oil product with ideal volatility and clean combustibility

By combining centrifugation and esterification reactions with differential evolution algorithms to optimize process parameters, the problems of low efficiency and high cost in biodiesel production were solved, achieving efficient production of high-quality biodiesel, reducing energy consumption and improving the model's generalization ability.

CN118931659AInactive Publication Date: 2024-11-12DALIAN MENGLIAN PETROCHEMICAL CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411131774.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing biodiesel production processes suffer from low efficiency, high cost, and unstable quality. In particular, the transesterification process involves high catalyst costs and slow reaction rates, resulting in poor biodiesel production quality.

Method used

By combining centrifugation with esterification, process parameters were optimized using multiple rounds of experimental data and differential evolution algorithms. An optimization model for esterification process parameters was constructed to solve for the optimal process parameters of crude oil esterification, including centrifugation, esterification, decolorization, and dehydration steps. The model was further optimized using adaptive variation factors and cross-validation strategies.

Benefits of technology

It improves the quality and production efficiency of biodiesel, reduces energy consumption, achieves high-precision and rapid optimization of process parameters, avoids the problem of the algorithm getting stuck in local optima, and improves the generalization ability of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118931659A_ABST
    Figure CN118931659A_ABST
Patent Text Reader

Abstract

The invention relates to a production process of an oil product with ideal volatility and clean combustibility, and belongs to the field of oil product production. The production process comprises the following steps: S1, carrying out centrifugal treatment on crude oil, and reserving upper-layer grease; s2, putting the grease into a pretreatment tank, and carrying out preliminary esterification reaction according to preset optimal process parameters; s3, introducing the crude oil subjected to the primary esterification reaction into a buffer tank, and carrying out further esterification reaction according to preset optimal process parameters; and S4, carrying out oil-water separation, decoloration, impurity removal and distillation on the crude oil subjected to the esterification reaction through a water segregator and a decoloration tank to obtain the biodiesel. According to the method, on the basis of multi-round experimental data, a differential evolution algorithm and a biodiesel quality evaluation model are combined, and an esterification reaction process parameter optimization model is constructed. Global search is carried out on the technological parameter population, and the optimal technological parameters of the crude oil esterification reaction are solved. According to the method, the model fitting precision is high, and optimization is accurate and rapid.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of oil product production, and in particular to a production process of oil products with ideal volatility and clean combustion. Background Art

[0002] The shortage of oil resources and environmental pollution have made people pay more attention to the development and utilization of green renewable oil products. Biodiesel is an energy with ideal volatility and clean, green and sustainable. As a fuel, biodiesel has greater advantages than conventional gasoline and diesel. The most concerned advantages are environmental advantages, such as its biodegradability, non-toxicity, low sulfur emissions, and fewer air pollutants and greenhouse gases other than nitrogen oxides. In addition, biodiesel has better lubricity, can reduce engine wear and has a higher oxygen content during combustion. The production and use of biodiesel has a positive effect on reducing the supply and demand of fossil energy, alleviating environmental pollution, and achieving sustainable economic and social development. The problem that needs to be solved in the production and preparation of biodiesel is the problem of production quality. Finding a fast and efficient process to produce biodiesel can effectively promote the competitiveness of biodiesel companies.

[0003] At present, the main method for producing biodiesel is the transesterification method, in which a catalyst is generally required. Commonly used catalysts include immobilized lipase, alkaline catalyst and acidic catalyst. The cost of immobilized lipase is too high, which is not conducive to large-scale production. The catalytic activity of alkaline catalysts is relatively high, but saponification reaction will occur in the alkaline catalytic method, which seriously affects the chemical reaction of generating biodiesel. When the acid catalytic method is used, the reaction rate is relatively slow and the reaction time is relatively long. On this basis, the acid-base two-step method was derived. The acid-base two-step method combines the advantages of the acid catalytic method and the alkaline catalytic method, but the process route is long and the cost is high. At present, there is no particularly effective way to solve the problem in China. Summary of the invention

[0004] Based on this, in order to solve the inefficiency problem in the biodiesel production process, improve the quality of biodiesel output and reduce the energy consumption of the production process, a production process for oil products with ideal volatility and clean combustion is provided.

[0005] The present invention is achieved through the following technical solution: A production process of an oil product with ideal volatility and clean combustion, characterized in that it includes the following steps:

[0006] S1: centrifuge the crude oil and retain the upper layer of oil;

[0007] S2: The treated crude oil is placed in a pretreatment tank, and then sulfuric acid is sprayed, steam is introduced, and insulation measures are taken according to preset optimal process parameters to achieve a preliminary esterification reaction between the crude oil and sulfuric acid;

[0008] S3: Putting the crude oil after the preliminary esterification reaction into a buffer tank, and introducing methanol and co-solvent according to the preset optimal process parameters for further esterification reaction;

[0009] S4: The crude oil after the esterification reaction is separated into oil and water by a water separator, and the oil layer in the water separator is decolorized and distilled by a decolorization tank to obtain biodiesel.

[0010] In one of the inventions, in step S3, the preset optimal process parameter acquisition steps are as follows:

[0011] S31: Conduct multiple rounds of crude oil esterification reaction experiments, record the density, freezing point, acid value, viscosity of the samples before and after the experiment, and the process parameters in the experiment, and calculate the esterification rate of the samples;

[0012] The present invention conducts multiple rounds of crude oil treatment experiments through centrifugation, esterification, decolorization, and dehydration, detects the influence of multiple process parameters on crude oil esterification reaction through experimental data, and measures the quality of biodiesel by measuring various physical and chemical indicators of samples before and after the experiment, providing data support for the construction of biodiesel quality evaluation model and esterification reaction process parameter process optimization model.

[0013] S32: Determine the quality indicators of biodiesel and build a biodiesel quality evaluation model;

[0014] S33: Determine the value range of the process parameters, construct a process parameter optimization model based on the differential evolution algorithm, and solve the input initial population of process parameters through the optimization model to obtain the optimal solution of the crude oil esterification reaction process parameters.

[0015] The present invention is based on multiple rounds of experimental data, combined with differential evolution algorithm and biodiesel quality evaluation model, to construct an esterification reaction process parameter optimization model. By performing a global search on the process parameter population, the optimal process parameters for crude oil esterification reaction are solved. The model fitting accuracy of the present invention is high, and the optimization is accurate and fast.

[0016] In one of the inventions, in step S32, the steps of constructing an esterification reaction process parameter optimization model are as follows:

[0017] S321: Standardize the experimental data;

[0018] S322: Determine biodiesel quality evaluation indicators, comprehensively consider various indicators and assign weights to each indicator;

[0019] S323: Calculate the score of each sample according to the quantitative evaluation formula and conduct quality assessment of biodiesel.

[0020] In one of the inventions, in step S33, the steps of constructing a process parameter optimization model based on a differential evolution algorithm are as follows:

[0021] S331: randomly initialize a preset number of individuals as an initial population, each individual corresponding to a value of a process parameter variable;

[0022] S332: inputting the initial population of process parameters into the biodiesel quality evaluation model to calculate the fitness value corresponding to each individual;

[0023] S333: If the outputted fitness value meets the requirement, then the optimal solution is outputted; if the outputted fitness value does not meet the requirement, then the initial population of process parameters is subjected to mutation, crossover and selection operations to generate a new generation population;

[0024] S334: Return the new generation population to S332 for loop processing until the model obtains the optimal solution or the model training reaches the maximum number of iterations, and output the optimal solution as the optimal process parameters.

[0025] In one of the inventions, in step S331, an initial population of size N is randomly generated in an n-dimensional solution space composed of a range of process parameter values, and the formula for taking the value of the j-th dimension of the i-th chromosome in the individuals of the initial population is as follows:

[0026] x ij (0) = x ijmin +(x ijmax -x ijmin )×R

[0027] In the formula, x ijmax 、x ijmin They represent the upper and lower bounds of the i-th chromosome respectively, and R represents a random number between (0,1).

[0028] In one of the inventions, in step S333, for any individual X in the t generation population i (t) Perform mutation operation to obtain a new mutant individual V i (t+1), the mutation operation formula is expressed as:

[0029] V i (t+1)=X a1 (t)+M(X a2 (t)-X a3 (t))

[0030] Where, X a1 (t), X a2 (t), X a3 (t) are the tth generation and X i (t) Different individuals, M is the parameter of balanced difference weight.

[0031] The calculation formula of M is as follows:

[0032]

[0033] Where M max 、M min Respectively represent the upper and lower limits of the adaptive variation factor, S a1 (t), S a2 (t), S a3 (t) represent three individuals in the t-th generation subpopulation whose fitness is ranked from best to worst.

[0034] In the mutation stage, the present invention adopts an adaptive mutation factor M(t) that can be adjusted with the change of the number of iterations, which solves the problem of insufficient search ability caused by the fixed factor of the differential evolution algorithm, avoids the problem that the algorithm falls into the local optimum due to the reduction of population diversity in the later stage of model training, and improves the accuracy of the solution.

[0035] In one of the inventions, in step S333, the variant individual V i (t+1) Use crossover operation to get the individual U to be selected i (t+1), the formula for the crossover operation is expressed as:

[0036]

[0037] In the formula, u ij (t+1) represents U i The j-th dimension component of (t+1), C represents the cross factor with a value range of (0,1), L ij Represents a random number between (0,1).

[0038] In one of the inventions, in step S333, individual U is selected by comparison i (t+1) and the current individual X i (t) fitness value, select the best value to update the population individuals, the formula is expressed as:

[0039]

[0040] In the formula, E(U i (t+1))、E(X i (t)) respectively represent the population individuals U i (t+1) and population individual X i (t) Crude oil esterification rate.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. Based on multiple rounds of experimental data, the present invention combines the differential evolution algorithm and the biodiesel quality evaluation model to construct an esterification reaction process parameter optimization model. By performing a global search on the process parameter population, the optimal process parameters for the crude oil esterification reaction are solved. The model fitting accuracy of the present invention is high, and the optimization is accurate and fast.

[0043] 2. In the population mutation stage of the differential evolution algorithm, the present invention adopts an adaptive mutation factor M(t) that can be adjusted with the change of the number of iterations, which solves the problem of insufficient search ability caused by the fixed factor of the differential evolution algorithm, avoids the problem that the algorithm falls into the local optimum due to the reduction of population diversity in the later stage of model training, and improves the accuracy of the solution.

[0044] 3. The present invention adopts a K-fold cross-validation strategy when inputting experimental data into the process parameter optimization model for training. Through multiple cross-validations of the training set, the possibility of overfitting can be reduced, and the situation where the model is overfitted on the training set can be avoided. The generalization ability of the model is effectively improved, and the optimal parameter combination is helped to select, so that the model can achieve the best performance on the validation set. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a step diagram of a production process of an oil product with ideal volatility and clean combustion according to Example 1 of the present invention;

[0046] Figure 2 for Figure 1 A step diagram for obtaining the preset optimal process parameters;

[0047] Figure 3 for Figure 2 Flow chart of constructing process parameter optimization model;

[0048] Figure 4 for Figure 3 Diagram of the steps for constructing a process parameter optimization model. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component at the same time. When a component is considered to be "fixed to" another component, it may be directly fixed on the other component or there may be a central component at the same time.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0052] Example 1: Please refer to Figure 1-Figure 4 This embodiment provides a production process for an oil product with ideal volatility and clean combustion, and the steps of the method are as follows:

[0053] S1: centrifuge the crude oil to retain the upper layer of fat. In this embodiment, the crude oil is centrifuged at 4200 rpm for 10 minutes using an ultra-high speed centrifuge.

[0054] S2: Put the treated crude oil into the pretreatment tank, then spray sulfuric acid, introduce steam and take insulation measures according to the preset optimal process parameters to achieve the initial esterification reaction between crude oil and sulfuric acid. This embodiment uses a JBJ stirring barrel and a YD type heater to form an esterification reaction pretreatment tank to achieve full mixing of the sample and sulfuric acid and accurately maintain the initial esterification reaction temperature.

[0055] S3: Put the crude oil after the initial esterification reaction into a buffer tank, and add methanol and co-solvent according to the preset optimal process parameters for further esterification reaction. In this embodiment, the buffer tank uses a ZCL type storage tank to store the initial esterification reaction raw materials, which is convenient for adding methanol and co-solvent.

[0056] In step S3, the preset optimal process parameters are obtained as follows:

[0057] S31: Conduct multiple rounds of crude oil esterification reaction experiments, record the density, freezing point, acid value, viscosity of the samples before and after the experiment, and the process parameters in the experiment, and calculate the esterification rate of the samples.

[0058] The crude oil was divided into multiple groups according to the preset quality, and each group of samples was subjected to two rounds of esterification reaction experiments. The density, freezing point, acid value and viscosity of each group of samples before and after the experiment and the process parameters of each group of experiments were recorded. The esterification reaction process parameters included: the concentration of sulfuric acid in the initial esterification reaction, the initial esterification reaction insulation time, the initial esterification reaction insulation temperature, the alcohol-oil mass ratio in the further esterification reaction, and the amount of water added in the further esterification reaction.

[0059] The sulfuric acid concentration, holding time, holding temperature, alcohol-oil mass ratio and water addition amount of each round of experiments are different. In this embodiment, by changing the esterification reaction process parameters, the density D of the sample before and after the experiment is measured by a hydrometer, the freezing point F of the sample before and after the experiment is measured by a freezing point meter, and the acid value a of the sample before and after the experiment is measured by an acid-base titration method. The esterification rate E of the final product biodiesel is calculated by the acid value of the sample before and after the test. Each sample is measured 3 times and the average is taken. The calculation formula of crude oil esterification rate is as follows:

[0060]

[0061] Wherein, a1 represents the acid value of the sample before esterification reaction, and a2 represents the acid value of the sample after esterification reaction.

[0062] This example conducts multiple rounds of treatment experiments on crude oil through centrifugation, esterification, decolorization, and dehydration. The experimental data detects the effects of the concentration of sulfuric acid in the initial esterification reaction, the insulation time of the initial esterification reaction, the insulation temperature of the initial esterification reaction, the alcohol-oil mass ratio in the further esterification reaction, and the amount of water added in the further esterification reaction on the crude oil esterification reaction, and measures the quality of biodiesel by measuring various physical and chemical indicators of the samples before and after the experiment. This provides data support for the construction of a process optimization model for esterification process parameters.

[0063] S32: The quality indicators of biodiesel include density, pour point, acid value and viscosity. Appropriate weights are assigned to each indicator. The steps to construct a comprehensive evaluation model are as follows:

[0064] S321: Standardize the experimental data to ensure that all indicators are at the same level. The standardization formula for any indicator data is as follows:

[0065]

[0066] Where y is the standard value of the indicator, x is the experimental value of the indicator, μ is the mean of the experimental value of the indicator, and σ is the standard deviation of the experimental value of the indicator.

[0067] S322: Determine biodiesel quality evaluation indicators, comprehensively consider various indicators and assign weights to each indicator.

[0068] S323: Calculate the score of each sample according to the quantitative evaluation formula to evaluate the quality of biodiesel. The quantitative evaluation formula is as follows:

[0069] S=w1D0+w2F0+w3a0+w4E0

[0070] Wherein, S represents the quality score of biodiesel, D0 represents the standard value of density, F0 represents the standard value of condensation point, a0 represents the standard value of acid value, E0 represents the standard value of esterification rate, and w1, w2, w3, and w4 represent the distribution weights of various indicators. In this embodiment, the weight values ​​of various indicators are: density D: 0.3, condensation point F: 0.3, acid value a: 0.2, and esterification rate E: 0.2.

[0071] S33: The steps of constructing a process parameter optimization model based on the differential evolution algorithm are as follows:

[0072] S331: Randomly initialize a preset number of individuals as the initial population, each individual corresponds to a value of a process parameter variable. Randomly generate an initial population of size N in the n-dimensional solution space composed of the process parameter value range X(0) = [X1(0), X2(0), ..., X N (0)], where each individual X i (0) = [x i1 (0),x i2 (0),…,x iD (0)] represents a set of solutions to the model, where D represents the number of process parameters in each set of solutions. The jth dimension of the i-th chromosome in the individuals of the initial population is taken as follows:

[0073] x ij (0) = x ijmin +(x ijmax -x ijmin )×R

[0074] In the formula, x ijmax , x ijmin They represent the upper and lower bounds of the i-th chromosome respectively, and R represents a random number between (0,1).

[0075] S332: Input the process parameter initial population into the biodiesel quality evaluation model to calculate the fitness value corresponding to each individual. In this embodiment, the comprehensive score of the population individual through the biodiesel quality evaluation model is used as the fitness value of the individual.

[0076] S333: If the output fitness value meets the requirements, then the optimal solution is output. If the output fitness value does not meet the requirements, then the initial population of process parameters is subjected to mutation, crossover and selection operations to generate a new generation population. In the differential evolution algorithm, for any individual X in the t generation population i (t) Perform mutation operation to obtain a new mutant individual Vi (t+1), the specific steps are as follows:

[0077] V i (t+1)=X a1 (t)+M(X a2 (t)-X a3 (t))

[0078] Where, X a1 (t), X a2 (t), X a3 (t) are the tth generation and X i (t) Different individuals, M is the parameter of balanced difference weight.

[0079] In the differential evolution algorithm, M is an adaptive mutation factor that can be adjusted as the number of iterations changes. The calculation formula of M is as follows:

[0080]

[0081] Where M max 、M min Respectively represent the upper and lower limits of the adaptive variation factor, S a1 (t), S a2 (t), S a3 (t) represent three individuals in the t-th generation subpopulation whose fitness is ranked from best to worst.

[0082] In the differential evolution algorithm, in order to increase the diversity of the population, the mutant individual V i (t+1) Use crossover operation to get the individual U to be selected i (t+1), the specific steps are as follows:

[0083]

[0084] In the formula, u ij (t+1) represents U i The j-th dimension component of (t+1), C represents the cross factor with a value range of (0,1), L ij Represents a random number between (0,1).

[0085] Select individual U by comparison i (t+1) and the current individual X i (t) is the fitness value, and the best value is selected to update the population individuals. The specific selection method is as follows:

[0086]

[0087] In the formula, E(U i (t+1)), E(X i(t)) respectively represent the population individuals U i (t+1) and population individual X i (t) Crude oil esterification rate.

[0088] In the mutation stage, this embodiment adopts an adaptive mutation factor M(t) that can be adjusted as the number of iterations changes, which solves the problem of insufficient search ability caused by the fixed factor of the differential evolution algorithm, avoids the problem that the algorithm falls into the local optimum due to the reduction of population diversity in the later stage of model training, and improves the accuracy of the solution.

[0089] S334: Return the new generation population to S332 for loop processing until the model obtains the optimal solution or the model training reaches the maximum number of iterations, and output the optimal solution as the optimal process parameter. In this embodiment, the population size N=40 and the number of iterations T=300.

[0090] The experimental data of each group of sample experiments are collected as the original data set and standardized. Randomly extract the experimental data of one round as the test set, and the experimental data of other rounds as the training set. Adopt the K-fold cross-validation strategy, take a part of the training set as the validation set for each training, and the rest as the training set for this training. This embodiment adopts the K-fold cross-validation strategy, and through multiple cross-validations of the training set, the possibility of overfitting can be reduced, and the situation where the model is overfitted on the training set can be avoided. Effectively improve the generalization ability of the model, help select the optimal parameter combination, and enable the model to achieve the best performance on the validation set.

[0091] S4: The crude oil after the esterification reaction is separated from the oil by a water separator, and the oil layer in the water separator is decolorized and distilled by a decolorization tank to obtain biodiesel. In this embodiment, the sample of the esterification reaction is separated from the oil by a separatory funnel, and a DY type decolorization tank with a heating function is used to remove the pigment and impurities in the oil layer in the water separator and dehydrate and dry it to obtain the final product biodiesel.

[0092] This embodiment constructs an esterification reaction process parameter optimization model based on the differential evolution algorithm, and uses the differential evolution algorithm based on the global search strategy of the population to achieve the solution of the optimal process parameters of the crude oil esterification reaction. The unique memory ability of the differential evolution algorithm enables it to dynamically track the current search situation and adjust the search measurement in time. It has a strong global convergence ability and effectively avoids the local optimal solution problem to obtain the global optimal solution. The dynamic optimization goal can be achieved by adjusting the weight of the fitness function and improving the applicability of the optimization result. By adjusting the adaptive variation factor in multiple iterations, the robustness and consistency of the results are improved. This embodiment has the characteristics of high model fitting accuracy and accurate and fast optimization.

[0093] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A process for producing an oil product having ideal volatility and clean combustion, characterized in that: The following steps are involved: S1: centrifuge the crude oil and retain the upper layer of oil; S2: The treated crude oil is placed in a pretreatment tank, and then sulfuric acid is sprayed, steam is introduced, and insulation measures are taken according to preset optimal process parameters to achieve a preliminary esterification reaction between the crude oil and sulfuric acid; S3: Putting the crude oil after the preliminary esterification reaction into a buffer tank, and introducing methanol and co-solvent according to the preset optimal process parameters for further esterification reaction; S4: The crude oil after the esterification reaction is separated into oil and water by a water separator, and the oil layer in the water separator is decolorized and distilled by a decolorization tank to obtain biodiesel.

2. The process for producing an oil product with ideal volatility and clean combustion according to claim 1, characterized in that: In step S3, the preset optimal process parameters are obtained as follows: S31: Conduct multiple rounds of crude oil esterification reaction experiments, record the density, freezing point, acid value, viscosity of the samples before and after the experiment, and the process parameters in the experiment, and calculate the esterification rate of the samples; S32: Determine the quality indicators of biodiesel and build a biodiesel quality evaluation model; S33: Determine the value range of the process parameters, construct a process parameter optimization model based on the differential evolution algorithm, and solve the input initial population of process parameters through the optimization model to obtain the optimal solution of the crude oil esterification reaction process parameters.

3. The process for producing an oil product with ideal volatility and clean combustion according to claim 2, characterized in that: In step S31, the calculation formula of crude oil esterification rate is as follows: Wherein, a1 represents the acid value of the sample before esterification reaction, and a2 represents the acid value of the sample after esterification reaction.

4. The process for producing an oil product with ideal volatility and clean combustion according to claim 2, characterized in that: In step S32, the steps of constructing a biodiesel quality evaluation model are as follows: S321: Standardize the experimental data; S322: Determine biodiesel quality evaluation indicators, comprehensively consider various indicators and assign weights to each indicator; S323: Calculate the score of each sample according to the quantitative evaluation formula and conduct quality assessment of biodiesel.

5. The process for producing an oil product with ideal volatility and clean combustion according to claim 2, characterized in that: In step S33, the steps of constructing a process parameter optimization model based on the differential evolution algorithm are as follows: S331: randomly initialize a preset number of individuals as an initial population, each individual corresponding to a value of a process parameter variable; S332: inputting the initial population of process parameters into the biodiesel quality evaluation model to calculate the fitness value corresponding to each individual; S333: If the outputted fitness value meets the requirement, then the optimal solution is outputted; if the outputted fitness value does not meet the requirement, then the initial population of process parameters is subjected to mutation, crossover and selection operations to generate a new generation population; S334: Return the new generation population to S332 for loop processing until the model obtains the optimal solution or the model training reaches the maximum number of iterations, and output the optimal solution as the optimal process parameters.

6. The process for producing an oil product with ideal volatility and clean combustion according to claim 5, characterized in that: In step S331, an initial population of size N is randomly generated in the n-dimensional solution space composed of the process parameter value range, and the formula for taking the j-th dimension of the i-th chromosome in the individuals of the initial population is as follows: x ij (0)=x ijmin +(x ijmax -x ijmin )×R In the formula, x ijmax 、x ijmin They represent the upper and lower bounds of the i-th chromosome respectively, and R represents a random number between (0,1).

7. The process for producing an oil product with ideal volatility and clean combustion according to claim 5, characterized in that: In step S333, for any individual X in the t generation population i (t) Perform mutation operation to obtain a new mutant individual V i (t+1), the mutation operation formula is expressed as: V i (t+1)=X a1 (t)+M(X a2 (t)-X a3 (t)) In the formula, X a1 (t), X a2 (t), X a3 (t) are the tth generation and X i (t) Different individuals, M is the parameter of balanced difference weight. The calculation formula of M is as follows: Where M max 、M min Respectively represent the upper and lower limits of the adaptive variation factor, S a1 (t), S a2 (t), S a3 (t) represent three individuals in the t-th generation subpopulation whose fitness is ranked from best to worst.

8. The process for producing an oil product with ideal volatility and clean combustion according to claim 7, characterized in that: In step S333, the variant individual V i (t+1) Use crossover operation to get the individual U to be selected i (t+1), the formula for the crossover operation is expressed as: In the formula, u ij (t+1) represents U i The j-th dimension component of (t+1), C represents the cross factor with a value range of (0,1), L ij Represents a random number between (0,1).

9. The process for producing an oil product with ideal volatility and clean combustion according to claim 8, characterized in that: In step S333, individual U is selected by comparison. i (t+1) and the current individual X i (t) fitness value, select the best value to update the population individuals, the formula is expressed as: In the formula, E(U i (t+1))、E(X i (t)) respectively represent the population individuals U i (t+1) and population individual X i (t) Crude oil esterification rate.

Citation Information

Patent Citations

  • Preparation method of biodiesel

    CN103320233A

  • Process parameter optimization method and device

    CN117422161A

  • Method and device for proportioning adhesive interlining rubber powder for policeman uniform

    CN118053528A

  • BP neural network internal mixing process multi-objective optimization method based on improved differential evolution

    CN118396464A