Scheduling methods, systems and storage media for secondary oil refining units

Abstract

This invention provides a scheduling method, system, and storage medium for secondary oil refining units. The scheduling method includes the following steps: establishing a material balance-based scheduling optimization model with the goal of maximizing enterprise profits and reducing oil consumption while increasing chemical production; establishing a corresponding proxy model based on the mechanism model of the secondary oil refining unit; combining the proxy model and the scheduling optimization model to construct a scheduling model aimed at maximizing enterprise profits and reducing oil consumption while increasing chemical production; and scheduling the secondary oil refining unit based on the scheduling model. This reduces refinery output of gasoline, kerosene, and diesel, increases the production of high-value chemical raw materials, maximizes refining enterprise profits, and adapts to today's volatile market environment.

Description

Technical Field

[0001] This invention relates to the field of industrial intelligent scheduling and optimization technology, and in particular to a scheduling method for a secondary oil refining unit, a scheduling system for a secondary oil refining unit, and a computer-readable storage medium. Background Technology

[0002] With the rapid development of science and technology, increasingly fierce market competition, and the continuous expansion of production scale, both domestic and foreign enterprises are turning their attention to energy conservation and emission reduction, hoping to improve raw material utilization under the same production conditions. At the same time, as domestic refined oil consumption enters a plateau or stabilizes and declines, the supply-side structure of refining is facing adjustment, and "reducing oil consumption and increasing chemical consumption" has become an important direction for adjusting the refining product structure.

[0003] Compared to other industrial processes, oil refining is characterized by large-scale production, complex processes, continuous logistics, continuous and stable production, and numerous interconnected units. However, most oil refining companies employ simplistic production scheduling schemes that fail to meet ever-changing market demands. These schemes typically rely solely on the experience of scheduling personnel, adjusting monthly plans by modifying scheduling model parameters and the actual production load of secondary units. This method of production scheduling optimization lacks global scope, leading to unnecessary losses for refining companies. Furthermore, the yield of crude oil converted into basic petrochemical feedstocks varies across domestic refineries: traditional fuel-type refineries achieve 5%–10%, while conventional integrated refining and chemical plants achieve 10%–20%. Therefore, existing oil refining technologies suffer from problems such as simplistic and poorly adjustable production scheduling schemes, as well as structural contradictions such as overcapacity in oil refining and insufficient capacity in chemical processing.

[0004] In order to overcome the above-mentioned defects in the existing technology, there is an urgent need in the field for a scheduling technology for secondary oil refining units, which can embed a high-precision proxy model into a traditional scheduling optimization model, thereby reducing the output of gasoline, kerosene and diesel in refineries and increasing the production of high-value chemical raw materials, so as to maximize the profits of refining and chemical enterprises and adapt to the current volatile market environment. Summary of the Invention

[0005] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed descriptions that follow.

[0006] To overcome the aforementioned deficiencies in the existing technology, this invention provides a scheduling method for secondary oil refining units, a scheduling system for secondary oil refining units, and a computer-readable storage medium. This method can embed a high-precision proxy model into a traditional scheduling optimization model and quickly and efficiently establish a model oriented towards reducing oil consumption and increasing chemical production. This reduces the output of gasoline, kerosene, and diesel fuel from refineries and increases the production of high-value chemical raw materials, thereby maximizing the profits of refining and chemical enterprises and adapting to today's volatile market environment.

[0007] Specifically, the scheduling method for a secondary refining unit according to the first aspect of the present invention includes the following steps: establishing a basic scheduling optimization model based on material balance with the goal of maximizing enterprise profits and reducing oil consumption while increasing chemical production; establishing a corresponding proxy model based on the mechanism model of the secondary refining unit; combining the proxy model with the basic scheduling optimization model to construct a scheduling model with the goal of maximizing enterprise profits and oriented towards reducing oil consumption while increasing chemical production; and scheduling the secondary refining unit based on the scheduling model.

[0008] Furthermore, in some embodiments of the present invention, the step of establishing a scheduling optimization basis based on material balance with the goal of maximizing enterprise profits and reducing oil consumption while increasing efficiency includes: determining an objective function with the goal of maximizing profits and reducing oil consumption based on the actual production situation of the secondary refining unit; determining decision variables related to the objective function based on the actual production load of the secondary refining unit, and determining a first constraint condition related to the objective function based on the upper limit of the production load, the upper limit of tank storage, and the lower limit of tank storage of the secondary refining unit; and establishing a scheduling optimization basic model based on the objective function, the decision variables, and the first constraint condition.

[0009] Furthermore, in some embodiments of the present invention, the expression of the objective function is as follows:

[0010] Where r = 1, 2, 3, ..., R

[0011] Where s = 1, 2, 3, ..., S

[0012] Where t = 1, 2, 3, ..., T

[0013] where i=1,2,3,...,I

[0014] SP=G·PG+M·PM+K·PK+PHS+PF-SY·PY-PW

[0015] Among them, g r Let m be the output of the r-th type of gasoline tank. s Let k be the output of the s-th type of kerosene tank.t Let G be the output of the t-th type of diesel fuel, G be the total output of gasoline fuel, M be the total output of kerosene fuel, K be the total output of diesel fuel, and H be the output of diesel fuel. i Let be the yield of the i-th chemical raw material, and PH be the pH value. i Let be the unit price of the i-th chemical raw material (yuan / ton), PHS be the revenue from the chemical raw material, SP be the enterprise revenue calculated in the simulation, PF be the total revenue from MTBE, sulfur, pentane foaming agent and liquefied petroleum gas, PG be the selling price of gasoline (yuan / ton), PM be the selling price of kerosene (yuan / ton), PK be the selling price of diesel (yuan / ton), SY be the total amount of mixed crude oil entering the secondary refining unit, PY be the cost price of mixed crude oil (yuan / ton), and PW be the sum of variable costs, fixed costs and external purchase costs.

[0016] Furthermore, in some embodiments of the present invention, the expression for the decision variable is as follows:

[0017] 0≤E n ≤W n Where n = 1, 2, 3, ..., N

[0018] Among them, E n W represents the actual production load of the nth unit. n This represents the upper limit of the production load for the nth device.

[0019] Furthermore, in some embodiments of the present invention, the first constraint condition includes:

[0020] 0≤G nj ≤GH nj Where n = 1, 2, 3, ..., N, j = 1, 2, 3, ..., J

[0021] 0≤Go nl ≤GoH nl Where n = 1, 2, 3, ..., N, l = 1, 2, 3, ..., L

[0022] Where n = 1, 2, 3, ..., N, l = 1, 2, 3, ..., L

[0023] Among them, G nj For the product output of the nth unit on the j-th side line, GH nj For the maximum output of the nth device on the j-th side line, Go nl For the l-th feed rate of n devices, GoH nl This represents the upper limit of the l-th feed rate for n devices.

[0024] Furthermore, in some embodiments of the present invention, the step of establishing a corresponding surrogate model based on the mechanistic model of the secondary refining unit includes: selecting multiple unit operating parameters that have a significant impact on the quality yield of the side-stream extracted product as input variables of the surrogate model according to the mechanistic model of the secondary refining unit, and selecting the corresponding quality yield as the target output variable; using a single sampling method to obtain a portion of the sample points required to establish the surrogate model; adjusting and simulating the input variables within the applicable range based on the mechanistic model to obtain comprehensive operating data to expand the initial sample set for establishing the surrogate model; and establishing the surrogate model using the Kriging surrogate model establishment method based on the initial sample set.

[0025] Furthermore, in some embodiments of the present invention, after establishing the proxy model, the scheduling method further includes the following steps: determining whether the accuracy of the proxy model meets the requirements; in response to the determination result that the accuracy of the proxy model meets the requirements, ending the construction process of the proxy model; and in response to the determination result that the accuracy of the proxy model does not meet the requirements, using an adaptive sampling algorithm to add new sample points of the key reaction function, and iterating the proxy model until the accuracy of the proxy model meets the requirements, or iterating to a preset maximum number of iterations.

[0026] Furthermore, in some embodiments of the present invention, the secondary refining unit includes at least one or more of the following: a first catalytic unit, a second catalytic unit, a pre-hydrogenation unit, a continuous reforming unit, a hydrocracking unit, a distillation adsorption isomerization unit, an extraction disproportionation benzene-toluene separation unit, a second hydrogenation unit, a fourth hydrogenation unit, and a light hydrocarbon recovery unit. The mechanistic model describes the operating mechanism of each of the aforementioned units included in the secondary refining unit.

[0027] Furthermore, in some embodiments of the present invention, the step of constructing a scheduling model aimed at maximizing enterprise profits and oriented towards reducing oil consumption and increasing chemical production by combining the proxy model and the scheduling optimization basic model includes: determining the set values ​​of the oil consumption reduction and increasing chemical production operation variables that conform to the design of the secondary refining unit; adjusting the values ​​of the input variables of the proxy model according to the set values ​​to determine the quality yields of various side-stream products of the secondary refining unit, wherein the input variables include at least one of actual production load, feedstock properties, tower pressure, reaction pressure, and reaction temperature; and adjusting the values ​​of the input variables of the proxy model again in response to any side-stream product's quality yield not meeting a preset second constraint condition. The following steps are taken: First, the quality yields of various side-stream products from the secondary refining unit are redefined. Second, in response to the condition that the quality yields of all side-stream products satisfy the second constraint, the quality yields of each side-stream product are input into the scheduling optimization base model, and it is determined whether they satisfy the first constraint. Third, in response to the condition that the quality yield of any side-stream product does not satisfy the first constraint, the initial data of the scheduling optimization base model is modified to correct the scheduling optimization base model, and it is re-determined whether the quality yields of each side-stream product satisfy the first constraint. Fourth, in response to the condition that the quality yields of all side-stream products satisfy the first constraint, the current scheduling optimization base model is used to determine the scheduling model.

[0028] Furthermore, in some embodiments of the present invention, the expression for the second constraint condition is as follows:

[0029] 0≤D n ≤W n Where n = 1, 2, 3, ..., N

[0030] 0≤R ny ≤X ny Where n=1,2,3,…,N,y=1,2,3,…,Y

[0031] Xx n ≤Tx n ≤Yx n Where n = 1, 2, 3, ..., N

[0032] 0≤Te n ≤Y n Where n = 1, 2, 3, ..., N

[0033] 0≤V n ≤Z n Where n = 1, 2, 3, ..., N

[0034] 0≤C nj Where n = 1, 2, 3, ..., N, j = 1, 2, 3, ..., J

[0035] 0≤M nf ≤Ye nf Where n = 1, 2, 3, ..., N, f = 1, 2, 3, ..., F

[0036] M n1 +M n2 +M n3 +...+M nf =1 where n = 1, 2, 3, ..., N, f = 1, 2, 3, ..., F

[0037] Among them, D n For the actual production load of the nth unit, W n R is the maximum load of the nth device. ny Let X be the feed amount of the y-th device. ny Tx is the upper limit of the y-th feed rate for the n-th device. n Let Xx be the raw material properties of the nth device. n Yx represents the lower limit of the range of raw material properties for the nth device. n Te represents the upper limit of the range of raw material properties for the nth device. n Y represents the reaction temperature of the nth device. n V represents the upper limit of the reaction temperature of the nth device. n Z represents the tower pressure of the nth unit. n C is the upper limit of the tower pressure of the nth device. nj M represents the extraction amount of the j-th side wire of the n-th device. nf Ye represents the mass yield of the f-th material in the n-th unit. nf This represents the upper limit of the mass yield of the f-th material in the n-th device.

[0038] Furthermore, in some embodiments of the present invention, the scheduling model is expressed with respect to the target values ​​of enterprise revenue and oil-to-chemicals ratio as follows:

[0039] Where r = 1, 2, 3...R

[0040] Where s = 1, 2, 3...S

[0041] Where t = 1, 2, 3...T

[0042] where i=1,2,3...I

[0043] SPN=NG·PGN+NM·PMN+NK·PKN+PHSN+PFN-SY·PY-PWN

[0044] SS = SPN - SP

[0045] Among them, Ng r For the rth type of product entering the gasoline tank, Nm s For the s-th type of product entering the kerosene tank, Nk t Let t be the product entering the diesel tank, NG be the total output of the new model entering the gasoline tank, NM be the total output of the scheduling model entering the kerosene tank, NK be the total output of the scheduling model entering the diesel tank, and NH be the product entering the diesel tank. i For the yield of the i-th chemical raw material, NPH i Let denoted as , where PHSN is the cost price of the i-th chemical raw material, PFN is the revenue from chemical raw materials in the scheduling model, PFN is the total revenue of the scheduling model for MTBE, sulfur, pentane foaming agent, and liquefied petroleum gas, PGN is the selling price of gasoline, PMN is the selling price of kerosene, PKN is the selling price of diesel, SY is the total amount of mixed crude oil entering the secondary refining unit, PY is the cost price of mixed crude oil, SPN is the enterprise revenue calculated by the scheduling model simulation, SP is the enterprise revenue calculated by the scheduling optimization basic model simulation, PWN is the sum of variable costs, fixed costs, and external purchase costs in the scheduling model, and SS is the enterprise revenue increment between the scheduling model and the scheduling optimization basic model.

[0046] Furthermore, in some embodiments of the present invention, the step of scheduling the secondary refining unit based on the scheduling model includes: using the scheduling model to perform a periodic production simulation calculation on the secondary refining unit to determine the actual production load, feed rate, and side-line product output of multiple secondary refining units that meet the goals of maximizing enterprise profits and reducing oil consumption while increasing chemical production; and determining the enterprise profits and oil-to-chemical ratio of the secondary refining unit based on the results obtained from the simulation calculation.

[0047] Furthermore, a scheduling system for a secondary refining unit according to a 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 configured to execute the computer instructions stored in the memory to implement the scheduling method for the secondary refining unit as described in any one of the first aspects of the present invention.

[0048] Furthermore, according to a third aspect of the present invention, a computer-readable storage medium is provided thereon storing computer instructions. When the computer instructions are executed by a processor, the scheduling method for a secondary refining unit as described in any one of the first aspects of the present invention is implemented. Attached Figure Description

[0049] The above-described features and advantages of the present invention will be better understood after reading the following detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings. In the drawings, components are not necessarily drawn to scale, and components having similar related characteristics or features may have the same or similar reference numerals.

[0050] Figure 1 A schematic diagram illustrating the steps of a scheduling method for a secondary refining unit provided according to some embodiments of the present invention is shown.

[0051] Figure 2 A schematic flowchart of a scheduling method for a secondary refining unit according to some embodiments of the present invention is shown. Detailed Implementation

[0052] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Although the description of the present invention is presented in conjunction with preferred embodiments, this does not mean that the features of the invention are limited to these embodiments. On the contrary, the purpose of describing the invention in conjunction with embodiments is to cover other options or modifications that may be derived based on the claims of the present invention. To provide a thorough understanding of the invention, many specific details will be included in the following description. The invention may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of the invention, some specific details will be omitted in the description.

[0053] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0054] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood as the orientations shown in the relevant paragraphs and accompanying drawings. These relative terms are for illustrative purposes only and do not imply that the described apparatus must be manufactured or operated in a specific orientation, and therefore should not be construed as limiting the invention.

[0055] It is understood that although terms such as "first," "second," and "third" 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 components, regions, layers, and / or parts discussed below may be referred to as second components, regions, layers, and / or parts without departing from some embodiments of the present invention.

[0056] To overcome the aforementioned deficiencies in the existing technology, this invention provides a scheduling method for secondary oil refining units, a scheduling system for secondary oil refining units, and a computer-readable storage medium. This system can embed a high-precision proxy model into a traditional scheduling optimization model to quickly and efficiently establish a model oriented towards reducing oil consumption and increasing chemical production. This reduces the output of gasoline, kerosene, and diesel fuel from refineries and increases the production of high-value chemical raw materials, thereby maximizing the profits of refining and chemical enterprises and adapting to today's volatile market environment.

[0057] In some non-limiting embodiments, the scheduling method for the secondary refining unit provided in the first aspect of the present invention can be implemented based on the scheduling system for the secondary refining unit provided in the second aspect of the present invention. Specifically, the scheduling system for the secondary refining unit is equipped with a memory and a processor. The memory includes, but is not limited to, the computer-readable storage medium provided in the third aspect of the present invention, on which computer instructions are stored. The processor is connected to the memory and is configured to execute the computer instructions stored in the memory to implement the scheduling method for the secondary refining unit provided in the first aspect of the present invention.

[0058] The following will describe the working principle of the above-mentioned scheduling system for secondary oil refining units using examples of scheduling methods for some secondary oil refining units. Those skilled in the art will understand that these embodiments of tank scheduling methods for oil refining processes are merely non-limiting implementations provided by this invention, intended to clearly demonstrate the main concepts of the invention and provide specific solutions convenient for public implementation, rather than limiting all functions or operating methods of the scheduling system for secondary oil refining units, and do not constitute a limitation on the executing entities or execution order of each step in these tank scheduling methods for oil refining processes.

[0059] Please refer to the following first. Figure 1 , Figure 1 A schematic diagram illustrating the steps of a scheduling method for a secondary refining unit provided according to some embodiments of the present invention is shown.

[0060] like Figure 1 As shown, in the process of scheduling optimization of secondary oil refining units, this invention can first establish a basic scheduling optimization model based on material balance, with the goal of maximizing enterprise profits and reducing oil consumption while increasing efficiency. Here, a linearized sequential model can be selected as the basic scheduling optimization model. Then, based on the mechanistic model of the secondary oil refining unit, this invention can establish a corresponding surrogate model with the goal of reducing computational resources and ensuring model accuracy. Combining this surrogate model with the basic scheduling optimization model, a scheduling model is constructed with the goal of maximizing enterprise profits and oriented towards reducing oil consumption while increasing efficiency.

[0061] In some embodiments, the secondary refining unit includes at least one or more of the following: a first catalytic unit, a second catalytic unit, a pre-hydrogenation unit, a continuous reforming unit, a hydrocracking unit, a distillation adsorption isomerization unit, an extraction disproportionation benzene-toluene separation unit, a second hydrogenation unit, a fourth hydrogenation unit, and a light hydrocarbon recovery unit. The mechanistic model describes the operating mechanism of each unit included in the secondary refining unit.

[0062] Please refer to the details. Figure 2 , Figure 2 A schematic flowchart of a scheduling method for a secondary refining unit according to some embodiments of the present invention is shown.

[0063] exist Figure 2 In the illustrated embodiment, during the establishment of this scheduling optimization basic model, the present invention can first determine the objective function, which aims to maximize efficiency and reduce oil consumption while increasing chemical production, based on the actual production situation of the secondary refining unit. The expression for the objective function is as follows:

[0064] Where r = 1, 2, 3, ..., R

[0065] Where s = 1, 2, 3, ..., S

[0066] Where t = 1, 2, 3, ..., T

[0067] where i=1,2,3,...,I

[0068] SP=G·PG+M·PM+K·PK+PHS+PF-SY·PY-PW

[0069] Among them, g r Let m be the output of the r-th type of gasoline tank. s Let k be the output of the s-th type of kerosene tank. t Let G be the output of the t-th type of diesel fuel, G be the total output of gasoline fuel, M be the total output of kerosene fuel, K be the total output of diesel fuel, and H be the output of diesel fuel. i Let be the yield of the i-th chemical raw material, and PH be the pH value. i Let represent the unit price (yuan / ton) of the i-th chemical raw material, PHS represent the revenue from the chemical raw material, SP represent the enterprise revenue calculated in the simulation, PF represent the total revenue from MTBE, sulfur, pentane foaming agent, and liquefied petroleum gas, PG represent the selling price (yuan / ton) of gasoline, PM represent the selling price (yuan / ton) of kerosene, PK represent the selling price (yuan / ton) of diesel, SY represent the total amount of mixed crude oil entering the secondary refining unit, PY represent the cost price (yuan / ton) of mixed crude oil, and PW represent the sum of variable costs, fixed costs, and external purchase costs.

[0070] Furthermore, the present invention can determine the decision variables of the objective function based on the actual production load of the secondary refining unit, and determine the first constraint condition of the objective function based on the upper limit of the production load, the upper limit of the tank storage, and the lower limit of the tank storage of the secondary refining unit. Then, a scheduling optimization basic model is established based on the objective function, the decision variables, and the first constraint condition.

[0071] Specifically, the expressions for the decision variables mentioned above are as follows:

[0072] 0≤E n ≤W n Where n = 1, 2, 3, ..., N

[0073] Among them, E n W represents the actual production load of the nth unit. n This represents the upper limit of the production load for the nth device.

[0074] The first constraint mentioned above includes:

[0075] 0≤G nj ≤GH nj Where n = 1, 2, 3, ..., N, j = 1, 2, 3, ..., J

[0076] 0≤Go nl ≤GoH nl Where n = 1, 2, 3, ..., N, l = 1, 2, 3, ..., L

[0077] Where n = 1, 2, 3, ..., N, l = 1, 2, 3, ..., L

[0078] Among them, G nj For the product output of the nth unit on the j-th side line, GH nj For the maximum output of the nth device on the j-th side line, Go nl For the l-th feed rate of n devices, GoH nl This represents the upper limit of the l-th feed rate for n devices.

[0079] Furthermore, in the process of establishing the corresponding proxy model, the present invention can select multiple unit operation parameters that have a significant impact on the quality yield of side-stream extracted products as input variables of the proxy model based on the mechanism model of the secondary refining unit, and select the corresponding quality yield as the target output variable.

[0080] Furthermore, please refer to Tables 1-3. Table 1 shows the actual production load of some secondary units in the sequential model. Table 2 shows the yield of some secondary units in the sequential model. Table 3 shows the output of the main products in the sequential model.

[0081] In an embodiment of an actual production unit at a refinery, this invention can utilize material balance methods to construct a scheduling sequence model. The input variable of this model is event data, and the adjustable variable is the actual production load. Using recent planned data from the refinery, the blended crude oil composition and actual production load entering the atmospheric and vacuum distillation unit are: Shengli Blend 53.13, Shengli Blend 23.80, Oman 13.98, Ural (Light) 9.09; Actual production load of atmospheric and vacuum distillation unit I is 8540 tons / day, and actual production load of atmospheric and vacuum distillation unit II is 6160 tons / day.

[0082] Furthermore, this invention can input the basic data of the scheduling model into the basic scheduling optimization model, and perform constraint condition judgments before and after the optimization calculation. If the constraints are not met, the actual production load and feed rate of the relevant equipment are modified and adjusted, and finally the actual production load, yield, and product output of the relevant equipment that meet the constraints are obtained.

[0083] Table 1 Actual Production Load of Some Secondary Units in the Sequential Model

[0084] Extraction and separation of disproportionated benzene and toluene 2310 Distillation Adsorption Isomerization 1225.875 Pentane oil hydrogenation 161.532 I Qi Fen 174.37 II. Gas Division 609 polypropylene 233.38 MTBE 273

[0085] Table 2. Yields of some secondary devices in the sequential model.

[0086]

[0087] Table 3. Output of Main Products in the Sequential Model

[0088] gasoline 2576.03 kerosene 2032.96 diesel fuel 3987.05 Chemical light oil 1081.65 benzene 210.6 Toluene 32.96 xylene 1025.2 polypropylene 232.12 styrene 109.76 MTBE 46.83 sulfur 593.25 Pentane foaming agent 151.69 Liquefied gas 811.54

[0089] Furthermore, this invention can determine the input and output variables of the corresponding device using a rigorous mechanistic model. It employs a single sampling method, combined with actual production data from the refinery, to perform partial sampling. Supplementary sampling is then conducted within the applicable range of the mechanistic model, and adjustments and simulations are performed on the input variables to obtain comprehensive operational data. This sampled data is then fed into a traditional mechanistic model to obtain output data. Subsequently, this invention can use the output data and sampled data as an initial sample set and, based on the fundamental theory of Kriging surrogate models, establish a corresponding surrogate model.

[0090] Furthermore, after establishing the proxy model, the scheduling method provided by this invention can also verify the accuracy of the proxy model to determine whether the accuracy of the proxy model meets the requirements.

[0091] Specifically, if the output data obtained in the first iteration is similar to the output data obtained from the mechanism model simulation, and meets the criteria for establishing a proxy model, the present invention can determine that the accuracy of the proxy model meets the requirements, thereby ending the proxy model construction process.

[0092] Conversely, if the output data obtained in the first iteration differs significantly from the output data obtained from the mechanism model simulation, and does not meet the criteria for establishing the surrogate model, this invention can determine that the accuracy of the surrogate model does not meet the requirements. It can then use an adaptive sampling algorithm to add new sample points for the key reaction function and iterate the surrogate model until the accuracy of the surrogate model meets the requirements, or iterates to the preset maximum number of iterations.

[0093] Please continue to refer to this. Figure 2 In the process of constructing a scheduling model for reducing oil consumption and increasing chemical production by combining the surrogate model and the scheduling optimization basic model, the above scheduling method first determines the setpoints of the operating variables for reducing oil consumption and increasing chemical production that conform to the design of the secondary refining unit. Then, it adjusts the values ​​of the input variables of the surrogate model according to the setpoints to determine the quality yield of various side-stream products of the secondary refining unit. Here, the input variables may include at least one of the following: actual production load, feedstock properties, tower pressure, reaction pressure, and reaction temperature.

[0094] Subsequently, if the quality yield of any side-stream product does not meet the preset second constraint, the present invention can readjust the values ​​of the input variables of the proxy model to redetermine the quality yield of various side-stream products of the secondary refining unit.

[0095] Conversely, if the quality yield of each sideline product satisfies the second constraint, this invention can input the quality yield of each sideline product into the scheduling optimization basic model and determine whether it satisfies the first constraint. In response to any sideline product's quality yield not satisfying the first constraint, this invention can modify the initial data of the scheduling optimization basic model, including one or more of the corresponding device's processing capacity, feed rate, and sideline direction, and simulate and run the new scheduling optimization basic model based on the optimized yield to verify whether the sideline extraction of each secondary device meets the set constraint, and re-determine whether the quality yield of each sideline product satisfies the first constraint. In response to all sideline products' quality yields satisfying the first constraint, this invention can determine the current scheduling optimization basic model as the scheduling model.

[0096] Furthermore, the expression for the second constraint condition mentioned above is as follows:

[0097] 0≤D n ≤W n Where n = 1, 2, 3, ..., N

[0098] 0≤R ny ≤X ny Where n=1,2,3,…,N,y=1,2,3,…,Y

[0099] Xx n ≤Tx n ≤Yx nWhere n = 1, 2, 3, ..., N

[0100] 0≤Te n ≤Y n Where n = 1, 2, 3, ..., N

[0101] 0≤V n ≤Z n Where n = 1, 2, 3, ..., N

[0102] 0≤C nj Where n = 1, 2, 3, ..., N, j = 1, 2, 3, ..., J

[0103] 0≤M nf ≤Ye nf Where n = 1, 2, 3, ..., N, f = 1, 2, 3, ..., F

[0104] M n1 +M n2 +M n3 +...+M nf =1 where n = 1, 2, 3, ..., N, f = 1, 2, 3, ..., F

[0105] Among them, D n For the actual production load of the nth unit, W n R is the maximum load of the nth device. ny Let X be the feed amount of the y-th device. ny Tx is the upper limit of the y-th feed rate for the n-th device. n Let Xx be the raw material properties of the nth device. n Yx represents the lower limit of the range of raw material properties for the nth device. n Te represents the upper limit of the range of raw material properties for the nth device. n Y represents the reaction temperature of the nth device. n V represents the upper limit of the reaction temperature of the nth device. n Z represents the tower pressure of the nth unit. n C is the upper limit of the tower pressure of the nth device. nj M represents the extraction amount of the j-th side wire of the n-th device. nf Ye represents the mass yield of the f-th material in the n-th unit. nf This represents the upper limit of the mass yield of the f-th material in the n-th device.

[0106] Furthermore, the scheduling model's expression for the target values ​​of firm profits and oil-to-chemical ratio is as follows:

[0107] Where r = 1, 2, 3...R

[0108] Where s = 1, 2, 3...S

[0109] Where t = 1, 2, 3...T

[0110] where i=1,2,3...I

[0111] SPN=NG·PGN+NM·PMN+NK·PKN+PHSN+PFN-SY·PY-PWN

[0112] SS = SPN - SP

[0113] Among them, Ng r For the rth type of product entering the gasoline tank, Nm s For the s-th type of product entering the kerosene tank, Nk t Let t be the product entering the diesel tank, NG be the total output of the new model entering the gasoline tank, NM be the total output of the scheduling model entering the kerosene tank, NK be the total output of the scheduling model entering the diesel tank, and NH be the product entering the diesel tank. i For the yield of the i-th chemical raw material, NPH i Let denot , where PHSN is the cost price of the i-th chemical raw material, PFN is the revenue from chemical raw materials in the scheduling model, PFN is the total revenue from MTBE, sulfur, pentane foaming agent, and liquefied petroleum gas in the scheduling model, PGN is the selling price of gasoline, PMN is the selling price of kerosene, PKN is the selling price of diesel, SY is the total amount of mixed crude oil entering the secondary refining unit, PY is the cost price of mixed crude oil, SPN is the enterprise revenue calculated by the scheduling model simulation, SP is the enterprise revenue calculated by the scheduling optimization basic model simulation, PWN is the sum of variable costs, fixed costs, and external purchase costs in the scheduling model, and SS is the increase in enterprise revenue between the scheduling model and the scheduling optimization basic model.

[0114] Furthermore, the present invention can use a scheduling model to perform cyclical production simulation calculations on secondary refining units to determine the actual production load, feed rate, and side-line product output of multiple secondary refining units that meet the goals of maximizing enterprise profits and reducing oil consumption while increasing chemical production. Then, based on the results obtained from the simulation calculations, the enterprise profits and oil-to-chemical ratio of the secondary refining units can be determined.

[0115] Further, please refer to Tables 4-6. Table 4 shows the actual production load of some secondary units in the new model for reducing oil consumption and increasing chemical production. Table 5 shows the yield of some secondary units in the new model for reducing oil consumption and increasing chemical production. Table 6 shows the output of the main products in the new model for reducing oil consumption and increasing chemical production.

[0116] As shown in Tables 4-6, in the above-mentioned refinery embodiments, the actual production load, yield, and product output of the relevant units were obtained under the constraints as follows:

[0117] Table 4. Actual Production Load of Secondary Units for the New Model of Oil Reduction and Chemical Enhancement

[0118] Extraction and separation of disproportionated benzene and toluene 2548.42 Distillation Adsorption Isomerization 1352.33 Pentane oil hydrogenation 292.5339366 I Qi Fen 210 II. Gas Division 665 polypropylene 260.68 MTBE 280

[0119] Table 5. Yields of secondary units in the new model for reducing oil consumption and increasing chemical production.

[0120]

[0121] Table 6. Output of Major Products Facing the New Model of Reducing Oil and Increasing Chemical Production

[0122] gasoline 2582.72 kerosene 2005.52 diesel fuel 3675.06 Chemical light oil 1081.65 benzene 232.33 Toluene 36.36 xylene 1131.01 polypropylene 259.28 styrene 109.76 MTBE 49.98 sulfur 586.18 Pentane foaming agent 274.75 Liquefied gas 905.87

[0123] Further, please refer to Tables 7 and 8. Table 7 shows the enterprise's (excluding tax) benefits under the sequential model, highlighting the key point of reducing oil consumption and increasing chemical production (oil-to-chemical ratio). Table 8 shows the enterprise's (excluding tax) benefits under the new model oriented towards reducing oil consumption and increasing chemical production, highlighting the key point of reducing oil consumption and increasing chemical production (oil-to-chemical ratio).

[0124] Table 7 shows the enterprise (excluding tax) benefits under the sequential model, highlighting the key points of reducing oil consumption and increasing chemical production (oil-to-chemical ratio).

[0125]

[0126] Table 8 shows the enterprise (excluding tax) benefits under the new oil reduction and chemical increase model, highlighting the oil-to-chemical ratio.

[0127]

[0128] As shown in Tables 7 and 8, the present invention can calculate the enterprise benefits based on the main product output of the sequential model in Table 3 and the main product output of the new model for reducing oil and increasing chemical production in Table 6, and obtain the enterprise benefits (excluding tax) under the sequential model, the key point of reducing oil and increasing chemical production (oil-to-chemical ratio) and the enterprise benefits (excluding tax) under the new model for reducing oil and increasing chemical production, as well as the key point of reducing oil and increasing chemical production (oil-to-chemical ratio).

[0129] According to Tables 1-8, under the new model, the oil-to-chemical ratio of fuel oil and chemical raw materials decreases, the daily crude oil processing revenue of refining enterprises increases by 0.4% per ton, and the daily cumulative revenue increases by 30,854.23 yuan.

[0130] In summary, the scheduling method, scheduling system, and computer-readable storage medium for secondary refining units provided by this invention can embed a high-precision proxy model into a traditional scheduling optimization model and quickly and efficiently establish a model oriented towards reducing oil consumption and increasing chemical production. This reduces the output of gasoline, kerosene, and diesel fuel from refineries and increases the production of high-value chemical raw materials, thereby maximizing the profits of refining and chemical enterprises and adapting to today's volatile market environment.

[0131] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0132] The prior description of this disclosure is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to this 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 this disclosure. Therefore, this disclosure is not intended to be limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A scheduling method for a secondary oil refining unit, characterized in that, Includes the following steps: With the goal of maximizing corporate profits and reducing oil consumption while increasing chemical production, a basic scheduling optimization model based on material balance is established. Based on the mechanistic model of the secondary refining unit, a corresponding proxy model is established; Determine the set values ​​of the oil reduction and chemical enhancement operation variables that conform to the design of the secondary refining unit; Based on the set values, the values ​​of the input variables of the proxy model are adjusted to determine the quality yield of various side-stream products of the secondary refining unit. The input variables include at least one of actual production load, raw material properties, tower pressure, reaction pressure, and reaction temperature. In response to any of the side-stream products failing to meet the preset second constraint, the values ​​of the input variables of the proxy model are adjusted again to redetermine the quality yields of the various side-stream products of the secondary refining unit. In response to the fact that the quality yield of each of the sideline products satisfies the second constraint, the quality yield of each of the sideline products is input into the scheduling optimization basic model, and it is determined whether it satisfies the first constraint. In response to any sideline product's quality yield failing to meet the first constraint, the initial data of the scheduling optimization base model is modified to correct the scheduling optimization base model, and the quality yield of each sideline product is reassessed to determine whether it meets the first constraint; and In response to the fact that the quality yield of each of the aforementioned sideline products satisfies the first constraint, the scheduling model is determined based on the current scheduling optimization base model; and The secondary refining unit is scheduled based on the aforementioned scheduling model.

2. The scheduling method as described in claim 1, characterized in that, The steps for establishing a scheduling optimization basis based on material balance, with the goal of maximizing enterprise profits and reducing oil consumption while increasing chemical production, include: Based on the actual production situation of the secondary refining unit, an objective function is determined with the goals of maximizing efficiency and reducing oil consumption while increasing chemical production. The decision variables for the objective function are determined based on the actual production load of the secondary refining unit, and the first constraint condition for the objective function is determined based on the upper limit of the production load, the upper limit of tank storage, and the lower limit of tank storage of the secondary refining unit; and A basic model for scheduling optimization is established based on the objective function, the decision variables, and the first constraint.

3. The scheduling method as described in claim 2, characterized in that, The expression for the objective function is as follows: Among them, g r For the production of the r-th type of gasoline in the tank, m s Let k be the output of the s-th type of kerosene tank. t Let G be the output of the t-th type of diesel fuel, G be the total output of gasoline fuel, M be the total output of kerosene fuel, K be the total output of diesel fuel, and H be the output of diesel fuel. i For the yield of the i-th chemical raw material, PH i Let be the unit price of the i-th chemical raw material, PHS be the revenue from the chemical raw material, SP be the enterprise revenue calculated in the simulation, PF be the total revenue from MTBE, sulfur, pentane foaming agent and liquefied petroleum gas, PG be the selling price of gasoline, PM be the selling price of kerosene, PK be the selling price of diesel, SY be the total amount of mixed crude oil entering the secondary refining unit, PY be the cost price of the mixed crude oil, and PW be the sum of variable costs, fixed costs and external purchase costs.

4. The scheduling method as described in claim 2, characterized in that, The expressions for the decision variables are as follows: Among them, E n W represents the actual production load of the nth unit. n This represents the upper limit of the production load for the nth device.

5. The scheduling method as described in claim 2, characterized in that, The first constraint includes: Among them, G nj For the product output of the nth unit on the j-th side line, GH nj For the maximum output of the nth device on the j-th side line, Go nl For the l-th feed rate of n devices, GoH nl E represents the upper limit of the l-th feed rate for n devices. n This represents the actual production load of the nth unit.

6. The scheduling method as described in claim 1, characterized in that, The steps for establishing a corresponding proxy model based on the mechanism model of the secondary oil refining unit include: Based on the mechanism model of the secondary refining unit, several unit operation parameters that have a significant impact on the quality yield of the side-stream extracted products are selected as input variables of the proxy model, and the corresponding quality yield is selected as the target output variable. A single sampling method is used to obtain a subset of sample points required to build the proxy model; Based on the aforementioned mechanism model, the input variables are adjusted and simulated within its applicable range to obtain comprehensive operational data, thereby expanding the initial sample set for establishing the proxy model; and Based on the initial sample set, the proxy model is established using the Kriging proxy model establishment method.

7. The scheduling method as described in claim 6, characterized in that, After establishing the agent model, the scheduling method further includes the following steps: Determine whether the accuracy of the proxy model meets the requirements; In response to the judgment result that the accuracy of the proxy model meets the requirements, the construction process of the proxy model ends; and In response to the judgment result that the accuracy of the surrogate model does not meet the requirements, an adaptive sampling algorithm is used to add new sample points to the key of the reaction function, and the surrogate model is iterated until the accuracy of the surrogate model meets the requirements, or the preset maximum number of iterations is reached.

8. The scheduling method as described in claim 6, characterized in that, The secondary refining unit includes at least one or more of the following: a first catalytic converter, a second catalytic converter, a pre-hydrogenation unit, a continuous reforming unit, a hydrocracking unit, a distillation adsorption isomerization unit, an extraction disproportionation benzene-toluene separation unit, a second hydrogenation unit, a fourth hydrogenation unit, and a light hydrocarbon recovery unit. The mechanistic model describes the operating mechanism of each of the aforementioned units included in the secondary refining unit.

9. The scheduling method as described in claim 1, characterized in that, The expression for the second constraint is as follows: Among them, D n For the actual production load of the nth unit, W n R is the maximum load of the nth device. ny Let X be the feed amount of the y-th device. ny Tx is the upper limit of the y-th feed rate for the n-th device. n Let Xx be the raw material properties of the nth device. n Yx represents the lower limit of the range of raw material properties for the nth device. n Te represents the upper limit of the range of raw material properties for the nth device. n Y represents the reaction temperature of the nth device. n V represents the upper limit of the reaction temperature of the nth device. n Z represents the tower pressure of the nth unit. n C is the upper limit of the tower pressure of the nth device. nj M represents the extraction amount of the j-th side wire of the n-th device. nf Ye represents the mass yield of the f-th material in the n-th unit. nf This represents the upper limit of the mass yield of the f-th material in the n-th device.

10. The scheduling method as described in claim 9, characterized in that, The scheduling model is expressed as follows regarding the target values ​​of enterprise profitability and oil-to-chemical ratio: Among them, Ng r For the rth type of product entering the gasoline tank, Nm s For the s-th type of product entering the kerosene tank, Nk t Let t be the product entering the diesel tank, NG be the total output of the new model entering the gasoline tank, NM be the total output of the scheduling model entering the kerosene tank, NK be the total output of the scheduling model entering the diesel tank, and NH be the product entering the diesel tank. i For the yield of the i-th chemical raw material, NPH i Let denoted as , where PHSN is the cost price of the i-th chemical raw material, PFN is the revenue from chemical raw materials in the scheduling model, PFN is the total revenue of the scheduling model for MTBE, sulfur, pentane foaming agent, and liquefied petroleum gas, PGN is the selling price of gasoline, PMN is the selling price of kerosene, PKN is the selling price of diesel, SY is the total amount of mixed crude oil entering the secondary refining unit, PY is the cost price of mixed crude oil, SPN is the enterprise revenue calculated by the scheduling model simulation, SP is the enterprise revenue calculated by the scheduling optimization basic model simulation, PWN is the sum of variable costs, fixed costs, and external purchase costs in the scheduling model, and SS is the enterprise revenue increment between the scheduling model and the scheduling optimization basic model.

11. The scheduling method as described in claim 10, characterized in that, The step of scheduling the secondary refining unit based on the scheduling model includes: The scheduling model is used to perform periodic production simulation calculations on the secondary refining units to determine the actual production load, feed rate, and side-stream product output of multiple secondary refining units that maximize corporate profits and achieve the goals of reducing oil consumption and increasing chemical production. Based on the results obtained from simulation calculations, the enterprise revenue and oil-to-chemical ratio of the secondary refining unit are determined.

12. A scheduling system for a secondary oil refining unit, characterized in that, include: Memory, on which computer instructions are stored; as well as A processor, connected to the memory, and configured to execute computer instructions stored in the memory to implement the scheduling method for a secondary refining unit as described in any one of claims 1 to 11.

13. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, the scheduling method for the secondary refining unit as described in any one of claims 1 to 11 is implemented.

Images