Optimization method and system for gasoline blending formula scheme and medium

Abstract

The invention provides a gasoline blending formula scheme optimization method, a gasoline blending formula scheme optimization system and a computer readable storage medium. The optimization method of the gasoline blending formula scheme comprises the following steps: determining a gasoline multi-objective optimization model according to objective functions and constraint conditions, wherein the objective functions are blending cost minimization and attribute excess minimization; determining a Pareto optimal solution set of the gasoline multi-objective optimization model through a swarm intelligence optimization algorithm; and determining an optimal solution in the Pareto optimal solution set as a gasoline blending formula scheme of the production demand according to the production demand. The optimization method of the gasoline blending formula scheme can comprehensively consider a plurality of key production quality indexes, solves the problem of complex optimization of a plurality of targets in the gasoline blending process, and has relatively strong global search capability, robustness and adaptivity, so that on the premise of ensuring the coordination of each production quality index, the optimization efficiency of the gasoline blending formula scheme is greatly improved. And an optimal blending formula scheme meeting a plurality of quality index requirements is found.

Description

Technical Field

[0001] The present invention relates to the technical field of gasoline blending, and in particular to a method for optimizing a gasoline blending formula, a system for optimizing a gasoline blending formula, and a computer-readable storage medium. Background Art

[0002] Gasoline blending mainly involves the oil blending process in the oil refining process. In the oil refining process, crude oil will be obtained after a series of refining processes, and component oils of different distillation ranges will be obtained. These component oils cannot directly meet the quality index requirements of various finished oils. Therefore, through the gasoline blending process, suitable component oils refined by different production units are selected, and then mixed in a certain proportion, so that the blended finished oil meets specific quality index requirements.

[0003] The gasoline blending process often requires comprehensive consideration of multiple factors so that the blended finished oil can meet multiple goals, such as increasing the octane number of gasoline, reducing sulfur content, and reducing harmful substance emissions. These goals often have a mutually restrictive relationship. However, the existing technology often has limitations when dealing with multiple goals of gasoline blending. When solving the gasoline blending formula, the existing technology is prone to fall into the local optimal solution, the solution result is greatly affected by the initial value, the calculation efficiency is low, and it lacks adaptive ability.

[0004] In order to overcome the above-mentioned defects of the prior art, there is an urgent need in the art for an optimization method for a gasoline blending formula scheme, which can comprehensively consider multiple key production quality indicators, solve the complex optimization problem of multiple objectives in the gasoline blending process, and have strong global search capability, robustness and adaptability, so as to find the best blending formula scheme that meets the requirements of multiple quality indicators while ensuring the coordination of various production quality indicators. Summary of the invention

[0005] A brief summary of one or more aspects is given below to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceived aspects, and is neither intended to identify the key or critical elements of all aspects nor to define the scope of any or all aspects. Its only purpose is to give some concepts of one or more aspects in a simplified form as a prelude to a more detailed description that will be given later.

[0006] In order to overcome the above-mentioned defects existing in the prior art, the present invention provides a gasoline blending formula optimization method, a gasoline blending formula optimization system, and a computer-readable storage medium, which can comprehensively consider multiple key production quality indicators, solve the complex optimization problem of multiple objectives in the gasoline blending process, and have strong global search ability, robustness and adaptability, so as to find the best blending formula that meets the requirements of multiple quality indicators under the premise of ensuring the coordination of various production quality indicators.

[0007] Specifically, the optimization method of the gasoline blending formula provided in accordance with the first aspect of the present invention comprises the following steps: S1: determining a gasoline multi-objective optimization model according to an objective function and constraints, wherein the objective function is minimization of blending cost and minimization of attribute excess; S2: determining a Pareto optimal solution set of the gasoline multi-objective optimization model by a swarm intelligence optimization algorithm; and S3: determining an optimal solution in the Pareto optimal solution set as the gasoline blending formula for the production demand according to production demand.

[0008] Preferably, in an embodiment of the present invention, the constraints include attribute constraints and formula constraints, and the formula constraints include formula upper and lower limit constraints and material balance constraints on the formula percentage of each component oil mass.

[0009] Preferably, in an embodiment of the present invention, the attribute constraint conditions include attribute constraint conditions based on volume fraction and attribute constraint conditions based on mass fraction.

[0010] Preferably, in one embodiment of the present invention, the attribute constraints based on volume fraction include upper and lower limits of one or more of the research octane number, motor octane number, anti-knock index, 10% evaporation temperature, 50% evaporation temperature, 90% evaporation temperature, terminal distillation point, vapor pressure, benzene content, aromatics content, and olefin content determined based on the volume fraction.

[0011] Preferably, in an embodiment of the present invention, the attribute constraint condition based on mass fraction includes an upper limit and a lower limit of one or more of sulfur content, oxygen content, and density determined based on mass fraction.

[0012] Preferably, in an embodiment of the present invention, the step S1 comprises: the objective function of minimizing the attribute excess is determined according to a weight coefficient of the attribute excess.

[0013] Preferably, in one embodiment of the present invention, step S1 includes: in response to the attribute needing to satisfy upward card edge optimization, downward card edge optimization or fixed value optimization, the attribute excess weight coefficient is a positive number; and in response to the attribute only needing to satisfy the attribute constraint condition, the attribute excess weight coefficient is 0.

[0014] Preferably, in one embodiment of the present invention, the step S2 comprises: S21: determining a decision variable according to the objective function, generating an initial population including a plurality of individuals as a first generation parent population in the search space of the decision variable; S22: performing non-dominated sorting on the plurality of individuals of the parent population according to the objective function, determining the number of dominated individuals of the individuals and the disposable individuals of the individuals; S23: grading the plurality of individuals into individual sets of various levels according to the number of dominated individuals of the plurality of individuals, wherein each level of the individual set corresponds to each level of non-dominated layer; S24: A new generation of sub-populations is generated by selection, crossover and mutation, and the sub-population is merged with the parent population to obtain a merged population; S25: non-dominated sorting is performed on the multiple individuals of the merged population according to the objective function, and the multiple individuals are graded, and the crowding distances of the multiple individuals are determined; S26: based on the merged population, a new generation of parent population is determined according to the sets of individuals at each level formed by grading the multiple individuals and the crowding distances of the multiple individuals; and S27: steps S24 to S26 are repeated according to the number of iterations to determine the Pareto optimal solution set of the gasoline multi-objective optimization model.

[0015] Preferably, in one embodiment of the present invention, the step S23 includes: S231: organizing the individuals whose number of dominated individuals is 0 into a first-level set, the first-level set is a first-level non-dominated layer, and reducing the number of dominated individuals of the disposable individuals of the individuals whose number of dominated individuals is 0 by 1; S232: organizing the individuals whose number of dominated individuals is 0 into a next-level set, the next-level set is a next-level non-dominated layer, and reducing the number of dominated individuals of the disposable individuals of the individuals whose number of dominated individuals is 0 by 1; and S233: repeating step S232 until all the individuals are divided into the individual sets of each level.

[0016] Preferably, in one embodiment of the present invention, the step S26 includes: S261: according to the individual sets of each level formed by grading the multiple individuals of the merged population, the individual sets are added to the new generation parent population according to the order of the levels; and S262: in response to the number of individuals in the new generation parent population exceeding the set population number after the new generation parent population is added to the individual set of the zth level, the individuals in the individual set of the zth level are selected to join the new generation parent population according to the size of the crowding distance, until the number of individuals in the new generation parent population is equal to the set population number, so as to form the new generation parent population.

[0017] In addition, the gasoline blending formula optimization system provided according to the second aspect of the present invention includes a memory and a processor. The memory stores computer instructions. The processor is connected to the memory and is configured to execute the computer instructions stored in the memory to implement the gasoline blending formula optimization method provided in any one of the above embodiments.

[0018] In addition, the computer-readable storage medium provided according to the third aspect of the present invention stores computer instructions, which, when executed by a processor, implement the method for optimizing the gasoline blending formula provided by any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above features and advantages of the present invention can be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or features may have the same or similar reference numerals.

[0020] Figure 1 A flow chart showing a method for optimizing a gasoline blending formula according to some embodiments of the present invention is shown;

[0021] Figure 2 A flow chart of a swarm intelligence optimization algorithm provided according to some embodiments of the present invention is shown;

[0022] Figure 3 A schematic diagram showing a property information table of each component oil provided according to a preferred embodiment of the present invention;

[0023] Figure 4 A schematic diagram showing an attribute constraint condition provided according to a preferred embodiment of the present invention is shown;

[0024] Figure 5 A schematic diagram showing a recipe constraint condition provided according to a preferred embodiment of the present invention is shown;

[0025] Figure 6 A schematic diagram showing a component oil price information table provided according to a preferred embodiment of the present invention;

[0026] Figure 7 A schematic diagram of an attribute optimization direction table provided according to a preferred embodiment of the present invention is shown;

[0027] Figure 8 A Pareto front diagram provided according to a preferred embodiment of the present invention is shown;

[0028] Figures 9A to 9C A formula ratio diagram of a Pareto optimal solution set provided according to a preferred embodiment of the present invention is shown; and

[0029] Fig.10 A schematic diagram of a system for optimizing a gasoline blending formula according to some embodiments of the present invention is shown.

[0030] Reference numerals:

[0031] 10: Optimization method of gasoline blending formula;

[0032] S1~S3: steps;

[0033] S21~S27: steps;

[0034] 801, 802, 803: solution set;

[0035] 1000: Gasoline blending formula optimization system;

[0036] 1010: memory;

[0037] 1011: Computer readable storage medium; and

[0038] 1020: Processor. DETAILED DESCRIPTION

[0039] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. Note that the aspects described below in conjunction with the accompanying drawings and specific embodiments are only exemplary and should not be construed as limiting the scope of protection of the present invention in any way.

[0040] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] In addition, the terms "upper", "lower", "left", "right", "top", "bottom", "horizontal" and "vertical" used in the following description should be understood as the directions shown in the paragraph and the related drawings. Such relative terms are only used for the convenience of description and do not mean that the device described therein must be manufactured or operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0042] It is understood that although the terms "first", "second", "third", etc. may be used herein to describe various components, regions, layers and / or parts, these components, regions, layers and / or parts should not be limited by these terms, and these terms are only used to distinguish different components, regions, layers and / or parts. Therefore, the first component, region, layer and / or part discussed below may be referred to as a second component, region, layer and / or part without departing from some embodiments of the present invention.

[0043] As mentioned above, the gasoline blending process often needs to comprehensively consider multiple factors so that the blended finished oil can meet multiple goals, and these goals often have a mutually restrictive relationship. However, the existing technology often has limitations when dealing with the problem of multiple goals of gasoline blending. When solving the gasoline blending formula, the existing technology is prone to fall into the local optimal solution, the solution result is greatly affected by the initial value, the calculation efficiency is low, and lacks adaptive ability.

[0044] In order to overcome the above-mentioned defects existing in the prior art, the present invention provides a gasoline blending formula optimization method, a gasoline blending formula optimization system, and a computer-readable storage medium, which can comprehensively consider multiple key production quality indicators, solve the complex optimization problem of multiple objectives in the gasoline blending process, and have strong global search ability, robustness and adaptability, so as to find the best blending formula that meets the requirements of multiple quality indicators under the premise of ensuring the coordination of various production quality indicators.

[0045] In some non-limiting embodiments, the gasoline blending formula optimization method provided in the first aspect of the present invention may be implemented via the gasoline blending formula optimization system provided in the second aspect of the present invention.

[0046] The following will first describe the working principle of the above-mentioned gasoline blending formula optimization system in conjunction with some embodiments of the gasoline blending formula optimization method. Those skilled in the art can understand that these embodiments of the gasoline blending formula optimization method are only some non-limiting implementation methods provided by the present invention, which are intended to clearly demonstrate the main concept of the present invention and provide some specific solutions that are convenient for the public to implement, rather than to limit all functions or all working modes of the gasoline blending formula optimization system. Similarly, the gasoline blending formula optimization system is also only a non-limiting implementation method provided by the present invention, and does not constitute a limitation on the execution subject and execution order of each step in these gasoline blending formula optimization methods.

[0047] Please refer to Figure 1 , Figure 1 A flow chart of a method for optimizing a gasoline blending formula according to some embodiments of the present invention is shown.

[0048] like Figure 1 As shown, the optimization method 10 for gasoline blending formula may include step S1: determining a gasoline multi-objective optimization model according to an objective function and constraint conditions, wherein the objective function is minimizing blending cost and minimizing excess of attributes.

[0049] The optimization system of gasoline blending formula can determine the gasoline multi-objective optimization model according to the objective function and constraint conditions. The gasoline blending process can form finished oil by blending multiple component oils. The objective function can be to minimize the blending cost and minimize the attribute excess. The constraint conditions can include attribute constraints and formula constraints. The attribute constraints can include attribute constraints based on volume fraction and attribute constraints based on mass fraction. The formula constraints can include upper and lower limit constraints of the formula and material balance constraints of the mass formula percentage of each component oil.

[0050] Here, the properties of each component oil and the blended finished oil may include: research octane number (RON) based on volume percentage, motor octane number (MON), anti-knock index (DON, Distribution Octane Number, or AKI, Anti-Knock Index), 10% evaporation temperature (T10, 10% Evaporation Temperature), 50% evaporation temperature (T50, 50% Evaporation Temperature), 90% evaporation temperature (T90, 90% Evaporation Temperature), final boiling point (FP, Final Boiling Point), vapor pressure (RVP, Reid Vapor Pressure), benzene content (BEN, Benzene), aromatics content (ARO, Aromatic Hydrocarbons Content), olefins content (OLF, Olefins Level), and sulfur content (SUL, Sulfur), oxygen content (OXY, Oxygen), and density (DEN, Density) based on mass percentage.

[0051] The optimization system of gasoline blending formula determines the attribute constraints, including the upper and lower limits of each attribute. Among the upper and lower limit constraints of attributes based on volume percentage, the determination of the attribute constraints of the research octane number (RON) of refined oil is taken as an example:

[0052]

[0053] Among them, the finished oil is formed by blending n component oils, CNj is the octane number of component j, ΔC Nj To consider the octane number C Nj The value of the mediation effect, is the corrected octane number, C Nmax is the upper limit of octane number, C Nmin is the lower limit of octane number, r j is the mass formula percentage of component j, ρ j is the density of component j.

[0054] In the upper and lower limit constraints of attributes based on mass percentage, take the determination of the attribute constraint conditions of sulfur content (SUL) of refined oil as an example:

[0055]

[0056] Among them, C sj is the sulfur content of component j, ΔC Sj To consider the sulfur content C Sj The value of the mediation effect, is the corrected sulfur content, Cs max is the upper limit of sulfur content, Cs min The lower limit of sulfur content.

[0057] In addition, the optimization system of the gasoline blending formula can set the formula constraints in the constraints of the gasoline multi-objective optimization model as:

[0058] lb≤r j ≤ub

[0059]

[0060] Wherein, lb is the lower limit of the mass formula percentage of component j, and ub is the upper limit of the mass formula percentage of component j.

[0061] In addition, the formulation constraints in the constraints of the gasoline multi-objective optimization model may also include formulation upper and lower limit constraints and material balance constraints of the formulation percentage of each component oil mass.

[0062] The optimization system of the gasoline blending formula can set an objective function. The objective function can include blending cost minimization and attribute excess minimization. The optimization system of the gasoline blending formula can determine the objective function of blending cost minimization according to the price of the component oil, and can determine the objective function of attribute excess minimization according to the weight coefficient of attribute excess.

[0063] Here, the optimization objective function can be set as:

[0064] minF(x)=[f1(x),f2(x)] T

[0065]

[0066] Among them, x is the decision variable, that is, x j is the mass formula percentage of component j, price j is the price of the component oil of component j; each component oil includes m properties, prop i is the predicted value of the i-th attribute, is the target value of the i-th attribute, ω i is the excess weight coefficient of the i-th attribute.

[0067] Here, when the i-th attribute needs to satisfy upward card edge optimization, downward card edge optimization or fixed value optimization, the weight coefficient ω i is a positive number; if the i-th attribute only needs to satisfy the attribute constraints (such as upper and lower limit constraints), the weight coefficient ω i is 0.

[0068] Therefore, according to the above objective function and constraints, the optimization system of gasoline blending formula can determine the gasoline multi-objective optimization model.

[0069] Please continue to refer to Figure 1 The gasoline blending formula optimization method 10 may include step S2: determining the Pareto optimal solution set of the gasoline multi-objective optimization model by a swarm intelligence optimization algorithm.

[0070] The swarm intelligence optimization algorithm is an optimization algorithm that simulates the behavior of biological groups in nature. It determines the optimal solution through information exchange and cooperation between individuals in the group. It has the advantages of parallelism, adaptability and robustness. In the optimization method of gasoline blending formula, the swarm intelligence optimization algorithm can simulate the interaction between different component oils and find the optimal blending ratio of gasoline blending formula that meets multiple quality index requirements through iterative calculation.

[0071] In a non-limiting embodiment, the optimization system for gasoline blending formula may first initialize the swarm intelligence optimization algorithm, and the initialization step may include setting the swarm size, swarm encoding method, and maximum number of iterations.

[0072] Please refer to Figure 2 , Figure 2 A flow chart of a swarm intelligence optimization algorithm provided according to some embodiments of the present invention is shown.

[0073] like Figure 2As shown, the optimization system for gasoline blending formula can execute step S21, encoding the decision variables determined by the objective function in the multi-objective optimization model of gasoline as individuals in the population, and then randomly generating an initial population including multiple individuals in the search space of the decision variables as the first-generation parental population P t . Here, the search space can be the formula constraints in the constraint conditions, that is, the upper and lower limits of the formula of the mass formula percentage (decision variable) of each component oil and the material balance constraint of the mass formula percentage of each component oil.

[0074] Preferably, to ensure that the optimization result can strictly meet the above-mentioned various constraint conditions, the optimization system for gasoline blending formula can set a constraint violation matrix according to the following formula:

[0075]

[0076] where g e (x) is an inequality constraint (i.e., the attribute constraint and the formula upper and lower limit constraint in the constraint conditions), h e (x) is an equality constraint (i.e., the percentage of the mass formula of each component oil in the constraint conditions satisfies the material balance constraint), q is the total number of constraints, and p is the number of inequality constraints. For the inequality constraint, if the solution x (i.e., the decision variable x) satisfies the inequality constraint, then cv e (x) ≤ 0; for the equality constraint, if the solution x satisfies the equality constraint, then cv e (x) = 0.

[0077] After that, the optimization system for gasoline blending formula can execute step S22: perform non-dominated sorting on multiple individuals of the parental population according to the objective function, and determine the number of dominant individuals of the individual and the individuals that can be dominated by the individual.

[0078] Perform non-dominated sorting on multiple individuals of the parental population P t . When a solution (i.e., the decision variable) is not inferior to other solutions in all objective functions, this solution is a non-dominated solution relative to other solutions. For example, for individuals x1 and x2 in the initial population, when f1(x1) < f1(x2) and f2(x1) < f2(x2), it means that individual x1 dominates individual x2, that is, solution x1 dominates solution x2. The optimization system for gasoline blending formula can set an index N(k) and an index S(k) for each individual x t in the parental population P k . The index N(k) is the number of individuals that dominate the individual x k , and the index S(k) is the set of individuals that the individual x k can dominate.

[0079] Please continue to refer to Figure 2 The swarm intelligence optimization algorithm may include step S23: grading the multiple individuals into individual sets at different levels according to the number of dominant individuals of the multiple individuals, and each individual set at each level corresponds to each non-dominated layer.

[0080] In a preferred embodiment, the optimization system of the gasoline blending formula may first execute step S231: the individuals whose number of dominated individuals is 0 are grouped into a first-level set, the first-level set being a first-level non-dominated layer, and the number of dominated individuals of the disposable individuals of the individuals whose number of dominated individuals is 0 is reduced by 1.

[0081] Specifically, the swarm intelligence optimization algorithm of the gasoline blending formula optimization system can find the individual x whose number of dominated individuals N(k) is 0 according to the number of dominated individuals N(k) of each individual determined in step S22. k1 , and these individuals x k1 The first-level set A is the first-level non-dominated layer. k1 is not dominated by other individuals, and individual x in the first-level set A k1 Do not dominate each other. Then, determine the individuals x in the first-level set A k1 The individuals dominated, that is, the individuals x in the first-level set A k1 The set S(k1) of individuals that can be controlled by . k2 The number of dominant individuals of the first level set A is reduced by 1, that is, the individual x that will be assigned to the first level set A k1 From individual x k2 subtracted from the number of dominant individuals.

[0082] Then, step S232 is executed again: the individuals whose number of dominated individuals is 0 are grouped into a next-level set, which is a next-level non-dominated layer, and the number of dominated individuals of the dominated individuals of the individuals whose number of dominated individuals is 0 is reduced by 1.

[0083] For example, the individuals x included in the set S(k1) k2 After the number of dominated individuals is reduced by 1, find the individual x whose number of dominated individuals N(k) is 0 k2 , and these individuals x k2 The second-level set B is the second-level non-dominated layer. k2 Divide the subtracted dominant individual x k1 In addition, it is not dominated by other individuals, and individual x in the second-level set B k2 do not dominate each other. Then, each individual x in the second-level set B k2 The set of individuals that can be controlled S(k2) includes individuals xk3 The number of dominant individuals of the second-level set B is reduced by 1, that is, the individual x that will be assigned to the second-level set B k2 From individual x k3 subtracted from the number of dominant individuals.

[0084] Afterwards, the gasoline blending formula optimization system may execute step S233, that is, repeat step S232 until the parent population P t All individuals in are divided into individual sets at each level. Each level of individual set corresponds to each level of Pareto frontier.

[0085] Please continue to refer to Figure 2 The swarm intelligence optimization algorithm may include step S24: generating a new generation of sub-populations through selection, crossover, and mutation, and merging the sub-populations with the parent population to obtain a merged population.

[0086] The optimization system of gasoline blending formula can be achieved by t Perform selection, crossover, and mutation operations to generate a new generation of subpopulation A t . Subpopulation A t With the parent population P t After merging, we can get the merged population N t The optimization system of gasoline blending formula can set the population size to N when initializing the population size, and merge the population N t The population size is 2N.

[0087] The optimization system of the gasoline blending formula scheme may execute step S25: non-dominated sorting is performed on the multiple individuals of the merged population according to the objective function, the multiple individuals are classified, and the crowding distances of the multiple individuals are determined.

[0088] Non-dominated sorting allows the algorithm to focus more on individuals that may become the optimal solution during the search process, so that operations such as selection, crossover, and mutation are more likely to produce new excellent solutions based on these excellent solutions, thereby improving the algorithm's search efficiency and convergence speed, and maintaining the diversity of the population.

[0089] Here, the optimization system of gasoline blending formula can be used to merge the population N t Multiple individuals are sorted non-dominatedly, for example, for the combined population N t Individual x in n1 and individual x n2 , when f1(x n1 ) <f1(x n2 ) and f2(x n1 ) <f2(x n2 ), it means that individual x n1 Dominant individual x n2 , that is, solve for xn1 Dominant solution x n2 By combining the population N t The non-dominated sorting of multiple individuals can determine the combined population N t The number of dominated individuals and disposable individuals of each individual.

[0090] Afterwards, according to the combined population N t The number of controlled individuals and the controllable individuals of each individual can be used to classify each individual. The optimization system of the gasoline blending formula can achieve the classification of each individual by a classification method including but not limited to steps S231 to S233.

[0091] In addition, the optimization system of gasoline blending formula can calculate the crowding distance Nd of the kth individual according to the following formula: k :

[0092]

[0093] Where A is the number of objective functions, f a (k+1) is the objective function value of the previous individual of the kth individual, f a (k-1) is the objective function value of the next individual after the kth individual, is the maximum value of the objective function, is the minimum value of the objective function. Calculating the crowding distance can effectively ensure the diversity of the population. For the first and last solutions of each non-dominated layer, its crowding distance can be directly set to a larger number.

[0094] Therefore, the combined population N t Each individual in can have two attributes, one is the non-dominated level formed after classification, and the other is the crowding distance.

[0095] The gasoline blending formula optimization system may execute step S26: based on the merged population, determine a new generation parent population according to the individual sets of each level formed by grading multiple individuals and the crowding distances of the multiple individuals.

[0096] The swarm intelligence optimization algorithm can set winning rules to compare the merged population N t Each individual in the combined population N t Each individual in the swarm intelligence optimization algorithm has two properties. The winning rule can be set as follows: when the non-dominated level of one individual is higher than that of another individual, the individual with the higher non-dominated level wins; when the non-dominated levels of the individuals are the same, the individual with the larger crowding distance wins.

[0097] In a non-limiting embodiment, the gasoline blending formula optimization system may execute step S261: according to the individual sets of each level formed by grading multiple individuals of the merged population, the individual sets are added to the new generation parent population in order of level.

[0098] By merging the parent population and the child population and selecting the best individuals, the search scope of the swarm intelligence optimization algorithm is expanded while the best solution is retained and the robustness of the swarm intelligence optimization algorithm is enhanced.

[0099] The optimization system of gasoline blending formula is to combine the population N t Each individual in the non-dominated sort is sorted, and each individual is graded into non-dominated levels to form a set of individuals at each level S t First, add the individuals in the highest non-dominated individual set S1 to the new generation parent population P t+1 middle.

[0100] Afterwards, the optimization system of the gasoline blending formula can execute step S262: in response to the number of individuals in the new generation parent population exceeding the set population number after the new generation parent population joins the z-th level individual set, individuals in the z-th level individual set are selected to join the new generation parent population according to the size of the crowding distance, until the number of individuals in the new generation parent population is equal to the set population number, so as to form a new generation parent population.

[0101] In determining the parent population P of the new generation t+1 During the process, the gasoline blending formula optimization system can monitor the parent population P t+1 After adding individuals from the individual set S1, if the parent population P t+1 If the population size is smaller than the population size N, the individuals in the next level of individual set S2 can be added to the new generation parent population P. t+1 Until the individual set S of the zth level is added i When the parent population P t+1 When the number of individuals exceeds the set population size N, stop joining the individual set S of the zth level i Then, according to the individual set S i The crowding distance of individuals in the parent population P is calculated, and individuals with large crowding distance are added to the parent population P. t+1 , until the parent population P t+1 The number of individuals is equal to the set population size N, thus forming a new generation of parent population P t+1 .

[0102] The swarm intelligence optimization algorithm can converge quickly through its flexible and adjustable parameters and low-complexity sorting mechanism. By setting the crowding distance, the optimization system of the gasoline blending formula can avoid the swarm intelligence optimization algorithm from converging too early during the iteration process, thereby ensuring population diversity, avoiding falling into local optimality, improving search quality, and making the final Pareto optimal solution set better reflect the trade-offs between different objectives.

[0103] Please continue to refer to Figure 2 The optimization system of the gasoline blending formula repeats steps S24 to S26 according to the number of iterations until the number of iterations is equal to the maximum number of iterations set during initialization. Thus, the Pareto optimal solution set of the gasoline multi-objective optimization model can be determined by the swarm intelligence optimization algorithm. Here, the optimization system of the gasoline blending formula can use the first level non-dominated layer in the population formed by the last iteration as the Pareto optimal solution set of the gasoline multi-objective optimization model.

[0104] Through the swarm intelligence optimization algorithm, the optimization system of gasoline blending formula can generate the optimal solution Pareto frontier under the premise of ensuring the coordination of various production quality indicators, so as to find the optimal gasoline formula composition that meets different production needs. In addition, the use of swarm intelligence optimization algorithm can avoid the problems existing in the existing technology, such as easy to fall into the local optimal solution, the solution result is greatly affected by the initial value, the calculation efficiency is low, and the lack of adaptive ability.

[0105] like Figure 1 As shown, the optimization method of the gasoline blending formula scheme continues to execute step S3: determining the optimal solution in the Pareto optimal solution set according to the production demand as the gasoline blending formula scheme of the production demand.

[0106] The following is a specific non-limiting preferred embodiment, based on which the optimization system of the gasoline blending formula proposed by the present invention is further described.

[0107] Please refer to Figure 3 , Figure 3 A schematic diagram of a property information table of each component oil provided according to a preferred embodiment of the present invention is shown.

[0108] like Figure 3 As shown, for a certain production batch, the adjusted oil may include 6 component oils, and the component oils may include 14 properties: research octane number (RON), motor octane number (MON), anti-knock index (DON), 10% evaporation temperature (T10), 50% evaporation temperature (T50), 90% evaporation temperature (T90), final distillation point (FP), vapor pressure (RVP), sulfur content (SUL), benzene content (BEN), aromatics content (ARO), olefin content (OLF), oxygen content (OXY), and density (DEN).

[0109] Among the six component oils, component 1 has a research octane number (RON) of 102%, a motor octane number (MON) of 91%, an antiknock index (DON) of 94.45%, a 10% evaporation temperature (T10) of 108°C, a 50% evaporation temperature (T50) of 145°C, a 90% evaporation temperature (T90) of 166°C, a final distillation point (FP) of 195°C, a vapor pressure (RVP) of 15KPa, a sulfur content (SUL) of 0mg / kg, a benzene content (BEN) of 0.6%, an aromatic content (ARO) of 79%, an olefin content (OLF) of 0%, an oxygen content (OXY) of 0%, and a density (DEN) of 850kg / m 3 . The research octane number (RON) of component 2 is 116.66%, the motor octane number (MON) is 102%, the anti-knock index (DON) is 109.33%, the 10% evaporation temperature (T10) is 35°C, the 50% evaporation temperature (T50) is 80°C, the 90% evaporation temperature (T90) is 100°C, the final distillation point (FP) is 130°C, the vapor pressure (RVP) is 60KPa, the sulfur content (SUL) is 3mg / kg, the benzene content (BEN) is 0%, the aromatic content (ARO) is 75%, the olefin content (OLF) is 0.62%, the oxygen content (OXY) is 18%, and the density (DEN) is 740kg / m 3 Component 3 has a research octane number (RON) of 70%, a motor octane number (MON) of 65%, an antiknock index (DON) of 69.67%, a 10% evaporation temperature (T10) of 35°C, a 50% evaporation temperature (T50) of 130°C, a 90% evaporation temperature (T90) of 100°C, a final distillation point (FP) of 185°C, a vapor pressure (RVP) of 45KPa, a sulfur content (SUL) of 0mg / kg, a benzene content (BEN) of 0.8%, an aromatic content (ARO) of 26.13%, an olefin content (OLF) of 22.1%, an oxygen content (OXY) of 0%, and a density (DEN) of 700kg / m 3 . The research octane number (RON) of component 4 is 92.3%, the motor octane number (MON) is 82.5%, the anti-knock index (DON) is 88.19%, the 10% evaporation temperature (T10) is 48°C, the 50% evaporation temperature (T50) is 83°C, the 90% evaporation temperature (T90) is 169°C, the final distillation point (FP) is 204°C, the vapor pressure (RVP) is 53.5KPa, the sulfur content (SUL) is 4mg / kg, the benzene content (BEN) is 0.96%, the aromatic content (ARO) is 23.1%, the olefin content (OLF) is 0%, the oxygen content (OXY) is 0%, and the density (DEN) is 720kg / m 3Component 5 has a research octane number (RON) of 80%, a motor octane number (MON) of 70%, an anti-knock index (DON) of 75%, a 10% evaporation temperature (T10) of 25°C, a 50% evaporation temperature (T50) of 35°C, a 90% evaporation temperature (T90) of 75°C, a final distillation point (FP) of 115°C, a vapor pressure (RVP) of 130KPa, a sulfur content (SUL) of 0mg / kg, a benzene content (BEN) of 10%, an aromatic content (ARO) of 0%, an olefin content (OLF) of 0%, an oxygen content (OXY) of 7%, and a density (DEN) of 627kg / m 3 . The research octane number (RON) of component 6 is 96.2%, the motor octane number (MON) is 93.7%, the anti-knock index (DON) is 94.9%, the 10% evaporation temperature (T10) is 69.6°C, the 50% evaporation temperature (T50) is 108.3°C, the 90% evaporation temperature (T90) is 134.1°C, the final distillation point (FP) is 199°C, the vapor pressure (RVP) is 55.6KPa, the sulfur content (SUL) is 4.2mg / kg, the benzene content (BEN) is 0%, the aromatic content (ARO) is 0%, the olefin content (OLF) is 1.4%, the oxygen content (OXY) is 0%, and the density (DEN) is 698.1kg / m 3 .

[0110] The optimization system of gasoline blending formula can determine the attribute constraints and formula constraints as the constraints of gasoline multi-objective optimization model.

[0111] Please refer to Figure 4 and Figure 5 , Figure 4 A schematic diagram showing an attribute constraint condition provided according to a preferred embodiment of the present invention is shown. Figure 5 A schematic diagram of recipe constraints provided according to a preferred embodiment of the present invention is shown.

[0112] like Figure 4As shown, in this preferred embodiment, the optimization system of the gasoline blending formula can use the upper and lower limits of 14 properties of the finished oil as property constraints. The upper limit of the research octane number (RON) of the finished oil is 92.5% and the lower limit is 92.1%, the upper limit of the motor octane number (MON) is 88% and the lower limit is 82.1%, the upper limit of the anti-knock index (DON) is 95% and the lower limit is 87.1%, the upper limit of the 10% evaporation temperature (T10) is 70% and the lower limit is 0%, the upper limit of the 50% evaporation temperature (T50) is 108°C and the lower limit is 0°C, the upper limit of the 90% evaporation temperature (T90) is 190°C and the lower limit is 0°C, the upper limit of the final distillation point (FP) is 204℃, lower limit is 0℃, upper limit of vapor pressure (RVP) is 63KPa, lower limit is 45KPa, upper limit of sulfur content (SUL) is 8mg / kg, lower limit is 0mg / kg, upper limit of benzene content (BEN) is 0.77%, lower limit is 0%, upper limit of aromatic content (ARO) is 34%, lower limit is 0%, upper limit of olefin content (OLF) is 13.5%, lower limit is 0%, upper limit of oxygen content (OXY) is 2.6%, lower limit is 0%, upper limit of density (DEN) is 775kg / m 3 , the lower limit is 720kg / m 3 .

[0113] like Figure 5 As shown, the optimization system of the gasoline blending formula scheme can use the upper and lower limits of the mass formula percentage of each component oil as formula constraints. The upper limit of the mass formula percentage of component 1 is 0.5, and the lower limit of the mass formula percentage is 0; the upper limit of the mass formula percentage of component 2 is 0.15, and the lower limit of the mass formula percentage is 0; the upper limit of the mass formula percentage of component 3 is 0.39, and the lower limit of the mass formula percentage is 0; the upper limit of the mass formula percentage of component 4 is 0.85, and the lower limit of the mass formula percentage is 0.25; the upper limit of the mass formula percentage of component 5 is 0.08, and the lower limit of the mass formula percentage is 0; the upper limit of the mass formula percentage of component 6 is 0.81, and the lower limit of the mass formula percentage is 0. The optimization system of the gasoline blending formula scheme can use the formula sum of the mass formula percentage of each component oil as 1 (that is, the material balance constraint of the mass formula percentage of each component oil) as a formula constraint.

[0114] In addition, please refer to Figure 6 and Figure 7 , Figure 6 FIG. 1 is a schematic diagram showing a component oil price information table provided according to a preferred embodiment of the present invention, Figure 7 A schematic diagram of a property optimization direction table provided according to a preferred embodiment of the present invention is shown.

[0115] The optimization system of the gasoline blending formula can determine the objective function of minimizing the blending cost according to the prices of the component oils, and can determine the weight coefficient in the objective function of minimizing the attribute excess according to the attribute optimization direction information.

[0116] like Figure 6 As shown, the price of component 1 is 6,500 yuan / ton, the price of component 2 is 5,200 yuan / ton, the price of component 3 is 8,200 yuan / ton, the price of component 4 is 7,000 yuan / ton, the price of component 5 is 8,000 yuan / ton, and the price of component 6 is 7,000 yuan / ton.

[0117] like Figure 7 As shown in the figure, the property optimization direction of the research octane number (RON) is downward card edge optimization, so the weight coefficient ω i It can be 1; the property optimization direction of the motor octane number (MON) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of the explosion resistance index (DON) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of 10% evaporation temperature (T10) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of 50% evaporation temperature (T50) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of 90% evaporation temperature (T90) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of the final distillation point (FP) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of vapor pressure (RVP) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of sulfur content (SUL) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of benzene content (BEN) is to meet the constraints of the upper and lower limits, so the weight coefficient ω i is 0; the property optimization direction of aromatic content (ARO) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of olefin content (OLF) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of oxygen content (OXY) is to meet the upper and lower limit constraints, so the weight coefficient ω i is 0; the property optimization direction of density (DEN) is to satisfy the upper and lower limit constraints, so the weight coefficient ω i is 0.

[0118] Therefore, by determining the objective function and constraint conditions, the optimization system of gasoline blending formula can determine the gasoline multi-objective optimization model.

[0119] The optimization system of the gasoline blending formula can initialize the swarm intelligence optimization algorithm, set the population size in the population scale to 100, the population encoding mode to real number mode, and the maximum number of iterations to 100000. Then, the optimization system of the gasoline blending formula determines the Pareto optimal solution set of the gasoline multi-objective optimization model through the initialized swarm intelligence optimization algorithm.

[0120] Please refer to Figure 8 , Figure 8 A Pareto front diagram provided according to a preferred embodiment of the present invention is shown.

[0121] like Figure 8 As shown, the Pareto front diagram consists of two dimensions: attribute excess and price of combined oil. The Pareto optimal solution set (MODE PF) finally formed by the swarm intelligence optimization algorithm may include a solution set 801 of a gasoline blending formula with the smallest attribute excess, a solution set 802 of a gasoline blending formula with the smallest cost, and a solution set 803 of a gasoline blending formula with balanced quality excess and cost.

[0122] Please refer to Figures 9A to 9C , Figures 9A to 9C A recipe ratio diagram of a Pareto optimal solution set provided according to a preferred embodiment of the present invention is shown.

[0123] like Fig.9A As shown, in the solution set 801 of the gasoline blending formula with the smallest excess mass, the formula ratio of component 1 is 21.76%, the formula ratio of component 2 is 14.4%, the formula ratio of component 3 is 23.49%, the formula ratio of component 4 is 40.2%, the formula ratio of component 5 is 0.07%, and the formula ratio of component 6 is 0.08%.

[0124] like Fig. 9B As shown, in the solution set 802 of the gasoline blending formula with the minimum cost, the formula ratio of component 1 is 22.14%, the formula ratio of component 2 is 14.44%, the formula ratio of component 3 is 22.01%, the formula ratio of component 4 is 41.4%, the formula ratio of component 5 is 0%, and the formula ratio of component 6 is 0.01%.

[0125] like Fig. 9CAs shown, in the solution set 803 of the gasoline blending formula with balanced quality excess and cost, the formula ratio of component 1 is 22.02%, the formula ratio of component 2 is 14.44%, the formula ratio of component 3 is 22.68%, the formula ratio of component 4 is 40.81%, the formula ratio of component 5 is 0.02%, and the formula ratio of component 6 is 0.03%.

[0126] In summary, the optimization method for the gasoline blending formula provided by the present invention is universal and flexible, can be applied to gasoline products of different types and requirements, can comprehensively consider multiple key production quality indicators, solve the complex optimization problem of multiple objectives in the gasoline blending process, and has strong global search capability, robustness and adaptability, so as to find the best blending formula that meets the requirements of multiple quality indicators under the premise of ensuring the coordination of various production quality indicators.

[0127] In addition, please refer to Fig.10 , Fig.10 A schematic diagram of a system for optimizing a gasoline blending formula according to some embodiments of the present invention is shown.

[0128] like Fig.10 As shown, the gasoline blending formula optimization system 1000 may be configured with a memory 1010 and a processor 1020. The memory 1010 includes but is not limited to the computer-readable storage medium 1011 provided in the third aspect of the present invention, on which computer instructions are stored. The processor 1020 is connected to the memory 1010 and is configured to execute the computer instructions stored in the memory to implement the gasoline blending formula optimization method provided in the first aspect of the present invention.

[0129] Although the above methods are illustrated and described as a series of actions for simplicity of explanation, it should be understood and appreciated that these methods are not limited by the order of the actions, because according to one or more embodiments, some actions may occur in a different order and / or concurrently with other actions from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art.

[0130] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips cited throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0131] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0132] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0133] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0134] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, a server, or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, wherein disk often reproduces data magnetically, while disc reproduces data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0135] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing a gasoline blending formula, characterized in that: Includes steps: S1: Determine a gasoline multi-objective optimization model according to an objective function and constraints, wherein the objective function is minimizing blending cost and minimizing excess of attributes; S2: Determine the Pareto optimal solution set of the gasoline multi-objective optimization model through a swarm intelligence optimization algorithm; and S3: Determine the optimal solution in the Pareto optimal solution set according to the production demand as the gasoline blending formula solution for the production demand.

2. The optimization method according to claim 1, characterized in that: The constraints include attribute constraints and recipe constraints.

3. The optimization method according to claim 2, characterized in that: The attribute constraints include attribute constraints based on volume fraction and attribute constraints based on mass fraction, and the formula constraints include upper and lower limit constraints and material balance constraints of the formula percentage of each component oil mass.

4. The optimization method according to claim 3, characterized in that: The attribute constraints based on volume fraction include upper and lower limits of one or more of the research octane number, motor octane number, anti-knock index, 10% evaporation temperature, 50% evaporation temperature, 90% evaporation temperature, terminal distillation point, vapor pressure, benzene content, aromatics content, and olefin content determined based on the volume fraction.

5. The optimization method according to claim 3, characterized in that: The mass fraction-based attribute constraints include upper and lower limits of one or more of sulfur content, oxygen content, and density determined based on mass fraction.

6. The optimization method according to claim 1, characterized in that: The step S1 comprises: The objective function of minimizing the attribute excess is determined according to the weight coefficient of the attribute excess.

7. The optimization method according to claim 6, characterized in that: The step S1 comprises: In response to the attribute needing to satisfy upward card edge optimization, downward card edge optimization or fixed value optimization, the weight coefficient of the attribute surplus is a positive number; and In response to the attribute only needing to satisfy the attribute constraint condition, the excess weight coefficient of the attribute is 0.

8. The optimization method according to claim 1, characterized in that: The step S2 comprises: S21: determining a decision variable according to the objective function, and generating an initial population including a plurality of individuals as a first-generation parent population in a search space of the decision variable; S22: performing non-dominated sorting on the plurality of individuals of the parent population according to the objective function, and determining the number of dominated individuals of the individuals and the disposable individuals of the individuals; S23: classifying the multiple individuals into individual sets at different levels according to the number of dominated individuals of the multiple individuals, wherein each individual set at each level corresponds to each non-dominated layer; S24: generating a new generation of sub-populations through selection, crossover, and mutation, and merging the sub-populations with the parent population to obtain a merged population; S25: performing non-dominated sorting on the multiple individuals of the merged population according to the objective function and grading the multiple individuals, and determining crowding distances of the multiple individuals; S26: Based on the merged population, determine a new generation parent population according to the individual sets of each level formed by the plurality of individuals being graded and the crowding distances of the plurality of individuals; and S27: Repeat steps S24 to S26 according to the number of iterations to determine the Pareto optimal solution set of the gasoline multi-objective optimization model.

9. The optimization method according to claim 8, characterized in that: The step S23 comprises: S231: The individuals whose number of dominated individuals is 0 are grouped into a first-level set, the first-level set being a first-level non-dominated layer, and the number of dominated individuals of the disposable individuals of the individuals whose number of dominated individuals is 0 is reduced by 1; S232: The individuals whose number of dominated individuals is 0 are grouped into a next-level set, the next-level set being a next-level non-dominated layer, and the number of dominated individuals of the disposable individuals of the individuals whose number of dominated individuals is 0 is reduced by 1; and S233: Repeat step S232 until all the individuals are divided into the individual sets of each level.

10. The optimization method according to claim 8, characterized in that: The step S26 comprises: S261: According to the individual sets of each level formed by the plurality of individuals of the merged population, the individual sets are added to the new generation parent population in order of level; and S262: In response to the number of individuals in the new generation parent population exceeding the set population size after the new generation parent population joins the z-th level individual set, the individuals in the z-th level individual set are selected to join the new generation parent population according to the size of the crowding distance until the number of individuals in the new generation parent population is equal to the set population size, so as to form the new generation parent population.

11. A gasoline blending formula optimization system, characterized in that: include: a memory having computer instructions stored thereon; as well as A processor is connected to the memory and is configured to execute computer instructions stored in the memory to implement the method for optimizing the gasoline blending formula according to any one of claims 1 to 10.

12. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the method for optimizing the gasoline blending formula according to any one of claims 1 to 10 is implemented.

Images