Crude oil dispatching scheme determination method and device and storage medium

Abstract

The invention provides a crude oil scheduling scheme determination method, a crude oil scheduling scheme determination device and a computer readable storage medium. The crude oil scheduling scheme determination method comprises the following steps: acquiring initial information and limiting conditions in a crude oil scheduling process; and establishing a crude oil scheduling optimization model of the atmospheric and vacuum distillation unit according to the initial information and the limiting conditions. The first optimization target of the crude oil scheduling optimization model comprises the step of minimizing the production state switching times of the atmospheric and vacuum distillation unit on the premise of meeting the limiting conditions; and inputting the initial information and the limiting conditions into the crude oil scheduling optimization model, and solving the crude oil scheduling optimization model to obtain a corresponding crude oil scheduling scheme. The method can be used for obtaining the crude oil scheduling scheme meeting the actual processing working condition, so that the production scheduling cost of the crude oil refining process is reduced, and the production scheduling efficiency of the crude oil refining process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crude oil scheduling optimization, and particularly to a method for determining a crude oil scheduling plan, a device for determining a crude oil scheduling plan, and a computer-readable storage medium. Background Art

[0002] The crude oil scheduling process covers multiple links such as the reception, transmission, storage, and processing of crude oil, and is a crucial part of the petroleum industry. Due to the fluctuations and instabilities in the crude oil market, and the need to comprehensively consider multiple influencing factors during the scheduling process, these all pose great challenges to schedulers in formulating a reasonable crude oil scheduling plan, resulting in the inability of existing crude oil scheduling plans to reasonably allocate resources during the crude oil scheduling process and increasing the ineffective loss of costs during the scheduling process. However, currently, formulating a crude oil scheduling plan still mainly relies on non-intelligent tools such as expert systems or work sheets for manual calculation and production scheduling. In addition, although mathematical programming methods and many intelligent optimization algorithms have had good successful application cases in multiple fields, in the field of crude oil scheduling, there is still a lack of efficient intelligent crude oil scheduling optimization technology. Traditional optimization methods are mainly based on pre-given algorithm parameters and lack the effective utilization of information during the optimization search process, thus limiting the ability to find the optimal solution.

[0003] In order to overcome the above-mentioned defects existing in the prior art, there is an urgent need in this field for an improved method for determining a crude oil scheduling plan, which is used to obtain a crude oil scheduling plan that conforms to the actual processing conditions, thereby reducing the production scheduling cost during the crude oil scheduling process and improving the production scheduling efficiency during the crude oil scheduling process. Summary of the Invention

[0004] The following gives a brief overview of one or more aspects to provide a basic understanding of these aspects. This overview is not an exhaustive survey of all contemplated aspects, and is neither 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 description that follows.

[0005] In order to overcome the above-mentioned defects existing in the prior art, the present invention provides a method for determining a crude oil scheduling plan, a device for determining a crude oil scheduling plan, and a computer-readable storage medium. By using an adaptive differential evolution algorithm to solve the crude oil scheduling optimization model established according to the actual conditions, it is used to obtain a crude oil scheduling plan that conforms to the actual processing conditions, thereby reducing the production scheduling cost during the crude oil refining process and improving the production scheduling efficiency during the crude oil refining process.

[0006] Specifically, the method for determining the above crude oil scheduling plan provided by the first aspect of the present invention includes the following steps: obtaining initial information and limiting conditions in the crude oil scheduling process; establishing an optimization model for crude oil scheduling of the atmospheric and vacuum distillation unit according to the initial information and the limiting conditions. The first optimization objective of the crude oil scheduling optimization model includes: minimizing the number of production state switches of the atmospheric and vacuum distillation unit on the premise of meeting the limiting conditions; and inputting the initial information and the limiting conditions into the crude oil scheduling optimization model and solving it to obtain the corresponding crude oil scheduling plan.

[0007] Further, in some embodiments of the present invention, the initial information includes at least one of the cycle of the crude oil scheduling task, the arrival date of the ship within the cycle, the type and quality of the crude oil transported by the ship, the oil separation situation of the crude oil storage tank group, the initial storage volume, the crude oil storage tank information, the initial storage volume of the wax residue oil storage tank, the fixed production value and fixed consumption value of the wax residue oil, the properties and yields of the crude oil. And / or the limiting conditions include at least one of the crude oil processing parameter limitations of the atmospheric and vacuum distillation unit, the mixed crude oil property parameter limitations, and the side line production parameter limitations.

[0008] Further, in some embodiments of the present invention, the step of establishing an optimization model for crude oil scheduling of the atmospheric and vacuum distillation unit according to the initial information and the limiting conditions includes: defining the variables of the crude oil scheduling optimization model according to the initial information; determining the optimization objective function of the crude oil scheduling optimization model according to the first optimization objective; and establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained various limiting conditions.

[0009] Further, in some embodiments of the present invention, the variables include at least one of the number of days in the cycle of the crude oil scheduling task, the number of ships, the number of atmospheric and vacuum distillation units, the number of residue oil types, the basic attributes of the oil types, the number of oil types, and the number of side line product types.

[0010] Further, in some embodiments of the present invention, the optimization objective function is:

[0011]

[0012] Where VD m,t is the total received amount received by the mth atmospheric and vacuum distillation unit from the crude oil storage tank on the tth day. OilChange m,t is used to represent whether the production state of the mth atmospheric and vacuum distillation unit changes on the tth day.

[0013] Further, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions includes: determining the inventory value of the virtual crude oil tank every day:

[0014]

[0015] Wherein, WJ j,t is the inventory of the virtual tank of oil type j on the t-th day. WV i,j,t is the amount of oil type j unloaded by the i-th ship on the t-th day. VT j,m,t is the amount of oil type j delivered to the m-th atmospheric and vacuum distillation unit on the t-th day; according to the input crude oil amount of the virtual crude oil tank to the atmospheric and vacuum distillation unit, determining the total processing amount processed by the atmospheric and vacuum distillation unit every day:

[0016]

[0017] Wherein, VT j,m,t is the amount of oil type j delivered to the m-th atmospheric and vacuum distillation unit on the t-th day; and determining the upper and lower limits of the total processing amount processed by the atmospheric and vacuum distillation unit every day to limit the total processing amount:

[0018]

[0019] Wherein, FDmin m is the lower limit of the total processing amount processed by the m-th atmospheric and vacuum distillation unit every day. FDmax m is the upper limit of the total processing amount processed by the m-th atmospheric and vacuum distillation unit every day.

[0020] Further, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions further includes: according to the total processing amount and the input crude oil amount, determining the upper limit of the processing ratio when each atmospheric and vacuum distillation unit processes various oil types to generate corresponding types of residue oil:

[0021] If XC m,n,t = 1

[0022] Wherein, PJ j,n is the upper limit of the proportion of the processing amount of the j-th type of crude oil in producing the n-th type of residue oil to the total processing amount of the atmospheric and vacuum distillation unit. XC m,n,t = 1 indicates that the m-th atmospheric and vacuum distillation unit produces the n-th type of residue oil on the t-th day. XC m,n,t = 0 indicates that the m-th atmospheric and vacuum distillation unit does not produce the n-th type of residue oil on the t-th day; according to the total processing amount and the input crude oil amount, determining the upper and lower limits of the mixing properties when each atmospheric and vacuum distillation unit processes oil types with basic properties of various oil types:

[0023]

[0024] Among them, Pmin m,l is the lower limit of the l-th mixed property of the m-th atmospheric and vacuum distillation unit. Pmax m,l is the upper limit of the l-th mixed property of the m-th atmospheric and vacuum distillation unit. P j,l is the l-th property value of the j-th type of oil; according to the input crude oil quantity, the side-line output ratio when the atmospheric and vacuum distillation unit processes various oil types to generate corresponding types of residue oil, and the amount of residue oil produced when the atmospheric and vacuum distillation unit produces residue feed, determine the upper limit of the residue feed produced when the atmospheric and vacuum distillation unit processes each oil type:

[0025] If XC m,n＝4,t = 1

[0026] Among them, FCY j,m,y＝6 is the side-line output ratio of residue oil when the m-th atmospheric and vacuum distillation unit processes oil type j. VCN m,n＝4,t is the amount of residue oil produced when the m-th atmospheric and vacuum distillation unit produces the residue feed on the t-th day. PN j is the upper limit of the proportion of the processing amount of oil type j in the total processing amount of the atmospheric and vacuum distillation unit when producing the residue feed; and determine the upper and lower limits of the daily side-line output of each atmospheric and vacuum distillation unit, and limit the daily side-line output of each atmospheric and vacuum distillation unit according to the daily input crude oil quantity into the atmospheric and vacuum distillation unit:

[0027]

[0028] Among them, FCYmin m,y is the daily output lower limit of the y-th side-line product of the m-th atmospheric and vacuum distillation unit. FCYmax m,y is the daily output upper limit of the y-th side-line product of the m-th atmospheric and vacuum distillation unit.

[0029] Furthermore, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained various constraint conditions further includes: determining the daily inventory value of each residue virtual tank:

[0030]

[0031] Among them, WR n,t is the inventory value of the virtual tank of the n-th type of residue oil on the t-th day. VRyield n is the fixed output value of the n-th type of residue oil per day. VRconsu n is the other fixed consumption value of the n-th type of residue oil per day; and determine the upper and lower limits of the daily inventory value of each residue virtual tank to limit the daily inventory value of each residue virtual tank:

[0032]

[0033] Among them, WRmin n is the lower limit of the virtual tank inventory of the nth residue oil. WRmax n is the upper limit of the virtual tank inventory of the nth residue oil.

[0034] Furthermore, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions further includes: determining the inventory value of the sulfur-containing wax oil virtual tank every day:

[0035]

[0036] Among them, WWS t is the inventory value of the sulfur-containing wax oil virtual tank on the tth day. VCNW m,n,t is the amount of wax oil produced when the mth atmospheric and vacuum distillation unit produces the nth residue oil on the tth day. WWSyield is the fixed output of the sulfur-containing wax oil virtual tank every day. WWSconsu is the fixed consumption of the sulfur-containing wax oil virtual tank every day; and determining the upper and lower limits of the inventory value of the sulfur-containing wax oil virtual tank every day to limit the inventory value of the sulfur-containing wax oil virtual tank every day:

[0037]

[0038] Among them, WWSmin is the lower limit of the inventory of the sulfur-containing wax oil virtual tank. WWSmax is the upper limit of the inventory of the sulfur-containing wax oil virtual tank.

[0039] Furthermore, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions further includes: determining the inventory value of the low-sulfur wax oil virtual tank:

[0040]

[0041] Among them, WWLS t is the inventory value of the low-sulfur wax oil virtual tank on the tth day. WWLSyrld is the fixed output of the low-sulfur wax oil virtual tank every day. WWLSconsu is the fixed consumption of the low-sulfur wax oil virtual tank every day; and determining the upper and lower limits of the inventory value of the low-sulfur wax oil virtual tank every day to limit the inventory value of the low-sulfur wax oil virtual tank every day:

[0042]

[0043] Among them, WWLSmin is the lower limit of the inventory of the low-sulfur wax oil virtual tank. WWLSmax is the upper limit of the inventory of the low-sulfur wax oil virtual tank.

[0044] Further, in some embodiments of the present invention, the step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions further includes: determining the upper and lower limits of the proportion of light oil processed by each atmospheric and vacuum distillation unit per day in the total processing volume according to the amount of crude oil input into the atmospheric and vacuum distillation unit every day and the total processing volume processed by the atmospheric and vacuum distillation unit every day, so as to limit the proportion of light oil in the total processing volume:

[0045]

[0046] wherein, LOmin m,t is the lower limit of the proportion of light oil processed by the m-th atmospheric and vacuum distillation unit on the t-th day. LOmax m,t is the upper limit of the proportion of light oil processed by the m-th atmospheric and vacuum distillation unit on the t-th day. LO is the set of light oil; determining the upper and lower limits of the proportion of heavy oil processed by each atmospheric and vacuum distillation unit per day in the total processing volume according to the amount of crude oil input into the atmospheric and vacuum distillation unit every day and the total processing volume processed by the atmospheric and vacuum distillation unit every day, so as to limit the proportion of heavy oil in the total processing volume:

[0047]

[0048] wherein, HOmin m,t is the lower limit of the proportion of heavy oil processed by the m-th atmospheric and vacuum distillation unit on the t-th day. HOmax m,t is the upper limit of the proportion of heavy oil processed by the m-th atmospheric and vacuum distillation unit on the t-th day. HO is the set of heavy oil; and limiting the types of residue oil produced by each atmospheric and vacuum distillation unit every day:

[0049]

[0050] wherein, XC m,n,t = 1 indicates that the m-th atmospheric and vacuum distillation unit produces the n-th type of residue oil on the t-th day.

[0051] Further, in some embodiments of the present invention, the step of inputting the initial information and the constraint conditions into the crude oil scheduling optimization model and solving it to obtain the corresponding crude oil scheduling plan includes: obtaining the population size and the maximum number of evolutions of the crude oil scheduling optimization model; in the outer loop, determining the initial switching times of the production status of the atmospheric and vacuum distillation unit according to the initial information; in the inner loop, determining a plurality of initial individuals according to the initial switching times, the first optimization objective and the second optimization objective. The second optimization objective includes: maximizing the operating load of the atmospheric and vacuum distillation unit on the premise of meeting the constraint conditions; determining the individual coding method of each of the initial individuals according to the population size, the maximum number of evolutions, and the variables of the crude oil scheduling optimization model to obtain an initial population; and optimizing the initial population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan.

[0052] Further, in some embodiments of the present invention, the step of determining the initial switching times of the production status of the atmospheric and vacuum distillation unit according to the initial information in the outer loop includes: determining the maximum value CNmax of the switching times of the production status of the atmospheric and vacuum distillation unit:

[0053] CNmax = m max ·(t max - 1)+1

[0054] where m max is the number of the atmospheric and vacuum distillation units. t max is the number of days of the cycle of the crude oil scheduling task; and determining the initial switching times of the production status of the atmospheric and vacuum distillation unit:

[0055]

[0056] where cn is the initial switching times of the production status of the atmospheric and vacuum distillation unit.

[0057] Further, in some embodiments of the present invention, the step of determining a plurality of initial individuals according to the initial switching times, the first optimization objective and the second optimization objective includes:

[0058] determining each of the initial individuals:

[0059] COPP k = [CN k , RANDP k , k ∈ {1, 2,..., Np}

[0060] where COPP k is the kth initial individual, and its dimension is cn + (1 + OilNum max·2)·(cn + m max )。OilNum max is the maximum number of oil types for delivering oil to the atmospheric and vacuum distillation unit. Np is the population size; and determining multiple random time nodes and multiple production plans for each of the initialized individuals:

[0061] CN k ={rand 1 , rand 2 , …, rand cn}

[0062]

[0063] where CN k is used to represent the random time node rand at which the production state of the atmospheric and vacuum distillation unit of the kth initialized individual switches. The number of the random time nodes is cn. RANDP k is used to represent the production plan plan. The number of the production plans is (cn + m max ).

[0064] Further, in some embodiments of the present invention, the step of optimizing the initialized population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan includes: defining each population individual as a target vector, and generating a mutant vector for each population individual according to each target vector, an initially set scaling factor, and a preset mutation strategy; generating a trial vector for each population individual according to the target vector, the mutant vector, an initially set crossover probability, and a preset recombination rule; determining a selection rule for each population individual, and comparing the trial vector with the target vector; and in response to the trial vector being superior to the target vector, updating the scaling factor and the crossover probability to obtain the corresponding crude oil scheduling plan.

[0065] Further, in some embodiments of the present invention, the step of optimizing the initialized population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan further includes: in response to the trial vector being superior to the target vector, defining an external storage set, and storing the replaced target vector in the external storage set to ensure the diversity of the population individuals.

[0066] In addition, the device for determining the above crude oil scheduling plan according to the second aspect of the present invention includes a memory and a processor. A computer instruction is stored on the memory. The processor, connected to the memory, is configured to execute the computer instruction stored on the storage module to implement the method for determining the crude oil scheduling plan provided in the first aspect of the present invention.

[0067] In addition, the above-mentioned computer-readable storage medium provided according to the third aspect of the present invention stores computer instructions, characterized in that when the computer instructions are executed by a processor, a method for determining a crude oil scheduling scheme provided according to the first aspect of the present invention is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] After reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings, the above features and advantages of the present invention can be better understood. In the drawings, the components are not necessarily drawn to scale, and components having similar relevant characteristics or features may have the same or similar reference numerals.

[0069] Figure 1 FIG. shows a production scheduling structure diagram of a crude oil scheduling scheme provided according to some embodiments of the present invention.

[0070] Figure 2 FIG. shows a schematic flow chart of a method for determining a crude oil scheduling scheme provided according to some embodiments of the present invention.

[0071] Figure 3 FIG. shows a schematic flow chart of solving an optimization model for crude oil scheduling provided according to some embodiments of the present invention.

[0072] Figure 4 FIG. shows a decision variable coding diagram provided according to some embodiments of the present invention.

[0073] Figure 5 FIG. shows a result diagram of optimizing a crude oil scheduling scheme provided according to some embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] The following specific embodiments illustrate the implementation manners 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 will be introduced in conjunction with the preferred embodiments, this does not mean that the features of this invention are limited to this implementation manner. On the contrary, the purpose of introducing the invention in conjunction with the implementation manner is to cover other alternatives or modifications that may be extended based on the claims of the present invention. In order to provide a deep understanding of the present invention, many specific details will be included in the following description. The present invention can also be implemented without these details. In addition, in order to avoid confusing or obscuring the focus of the present invention, some specific details will be omitted in the description.

[0075] In the description of the present invention, it should be noted that, unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0076] In addition, the "upper", "lower", "left", "right", "top", "bottom", "horizontal", and "vertical" used in the following description should be understood as the orientations shown in this section and the relevant drawings. This relative term is only for convenience of description and does not mean that the device described needs to be manufactured or operated in a specific orientation, so it should not be construed as a limitation to the present invention.

[0077] It can be understood that although terms such as "first", "second", and "third" can 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 can be referred to as the second component, region, layer, and / or part without departing from some embodiments of the present invention.

[0078] As mentioned above, currently, the formulation of crude oil scheduling plans still mainly relies on non-intelligent tools such as expert systems or work sheets for manual calculation of production scheduling. In addition, although mathematical programming methods and many intelligent optimization algorithms have had good successful application cases in many fields, in the field of crude oil scheduling, there is still a lack of efficient intelligent crude oil scheduling optimization technologies. Traditional optimization methods are mainly based on pre-given algorithm parameters and lack the effective utilization of information in the optimization search process, thus limiting the ability to find the optimal solution.

[0079] In order to overcome the above-mentioned defects existing in the prior art, the present invention provides a method for determining a crude oil scheduling plan, a device for determining a crude oil scheduling plan, and a computer-readable storage medium, which can solve the crude oil scheduling optimization model established according to actual working conditions by using an adaptive differential evolution algorithm to obtain a crude oil scheduling plan that conforms to the actual processing conditions, thereby reducing the production scheduling cost in the crude oil refining process and improving the production scheduling efficiency in the crude oil refining process.

[0080] In some non - restrictive embodiments, the method for determining the above - mentioned crude oil scheduling plan provided by the first aspect of the present invention can be implemented based on the device for determining the above - mentioned crude oil scheduling plan provided by the second aspect of the present invention. Specifically, the device for determining the above - mentioned crude oil scheduling plan provided by the second aspect of the present invention includes a memory and a processor. Here, the memory includes but is not limited to the computer - readable storage medium provided by the aforementioned third aspect, on which computer instructions are stored. The controller is connected to the memory and is configured to execute the computer instructions stored on the memory to implement the method for determining the crude oil scheduling plan provided by the first aspect of the present invention.

[0081] The working principle of the above - mentioned device for determining the crude oil scheduling plan will be described below in conjunction with some embodiments of the method for determining the crude oil scheduling plan. Those skilled in the art can understand that these embodiments of the determination method are only some non - restrictive implementation manners provided by the present invention, aiming to clearly show the main concept of the present invention and provide some specific solutions convenient for the public to implement, rather than restricting all functions or all working modes of the device for determining the crude oil scheduling plan. Similarly, the device for determining the crude oil scheduling plan is also only a non - restrictive implementation manner provided by the present invention, and does not limit the execution subject and execution order of each step in these methods for determining the crude oil scheduling plan.

[0082] Specifically, please refer to Figure 1 and Figure 2 . Figure 1 shows the production scheduling structure diagram of the crude oil scheduling plan provided by some embodiments of the present invention. Figure 2 shows the schematic flow diagram of the method for determining the crude oil scheduling plan provided by some embodiments of the present invention.

[0083] As Figure 1 shown, the entire crude oil scheduling process starts from counting crude oil resources. The crude oil resources include the crude oil resources loaded by the crude oil - transporting ships and the crude oil resources stored in the physical tank farms. Then, the crude oil formula to be transported to the atmospheric and vacuum distillation processing units for processing is planned. During this period, multiple constraint conditions for device processing and production need to be satisfied, and finally, the primary products after processing are obtained.

[0084] As Figure 2 shown, the above - mentioned device for determining the crude oil scheduling plan provided by the second aspect of the present invention can first obtain the initial information and constraint conditions in the crude oil scheduling process.

[0085] In some embodiments, the initial information includes at least one of the cycle of the crude oil scheduling task, the arrival date of the vessel within the cycle, the type and quality of the crude oil transported by the vessel, the oil separation situation of the crude oil storage tank group, the initial storage quantity, the crude oil storage tank information, the initial storage quantity of the wax residue oil storage tank, the fixed production value and fixed consumption value of the wax residue oil, the properties and yield of the crude oil. The restrictive conditions include at least one of the crude oil processing parameter restrictions of the atmospheric and vacuum distillation unit, the mixed crude oil property restrictions, and the side line output parameter restrictions.

[0086] Specifically, please refer to Tables 1 to 8 for reference. Table 1 shows the information table of the arrival date of the crude oil transported by the vessel provided according to some embodiments of the present invention. Table 2 shows the information table of the oil separation situation, initial storage quantity and crude oil storage tank information of the crude oil storage tank group provided according to some embodiments of the present invention. Table 3 shows the information table of the initial storage quantity of the wax residue oil storage tank and the fixed production value and fixed consumption value of the wax residue oil provided according to some embodiments of the present invention. Table 4 shows the information table of the properties of the crude oil provided according to some embodiments of the present invention. Table 5 shows the information table of the yield of the crude oil provided according to some embodiments of the present invention. Table 6 shows the crude oil processing parameter restriction table of the atmospheric and vacuum distillation unit provided according to some embodiments of the present invention. Table 7 shows the crude oil property parameter restriction table of the atmospheric and vacuum distillation unit provided according to some embodiments of the present invention. Table 8 shows the side line output parameter restriction table of the atmospheric and vacuum distillation unit provided according to some embodiments of the present invention.

[0087] Table 1 Information Table of the Arrival Date of the Crude Oil Transported by the Vessel

[0088] Vessel Number Crude Oil Number Crude Oil Quantity Loaded (tons) Arrival Time at Port (the t-th day) V1 No.11 122000 1 V2 No.3 132000 2 V3 No.2 73000 2 V4 No.11 33000 3 V5 No.11 30000 7 V6 No.12 130000 7 V7 No.1 130000 9

[0089] Further, in the embodiment shown in Table 1, the above initial information includes the cycle of the crude oil scheduling task, the arrival date of the vessel within the cycle, and the type and quality of the crude oil transported by the vessel. Here, the cycle of the crude oil scheduling task is 10 days. Vessel numbers V1 to V7 arrive at the port on the 1st, 2nd, 3rd, 7th, and 9th days within the cycle and transport crude oils numbered No.11, No.3, No.2, No.11, No.11, No.12, and No.1 respectively.

[0090] Table 2 Information Table of the Oil Separation Situation, Initial Storage Quantity and Crude Oil Storage Tank Information of the Crude Oil Storage Tank Group

[0091]

[0092] Further, in the embodiment shown in Table 2, the above initial information includes the oil separation situation of the crude oil storage tank group, the initial storage quantity, and the crude oil storage tank information.

[0093] Table 3 Information Table of the Initial Storage Quantity of the Wax Residue Oil Storage Tank and the Fixed Production Value and Fixed Consumption Value of the Wax Residue Oil

[0094]

[0095] Further, in the embodiment shown in Table 3, the above-mentioned initial information includes the initial storage volume of the wax residue oil storage tank, the fixed production value and the fixed consumption value of the wax residue oil.

[0096] Table 4 Property Information Table of Crude Oil

[0097]

[0098] Further, in the embodiment shown in Table 4, the above-mentioned initial information includes the property information of the crude oil participating in the scheduling.

[0099] Table 5 Yield Information Table of Crude Oil

[0100]

[0101] Further, in the embodiment shown in Table 5, the above-mentioned initial information includes the yield information of the crude oil participating in the scheduling.

[0102] Table 6 Limitation Table of Crude Oil Processing Parameters of Atmospheric and Vacuum Distillation Unit

[0103]

[0104]

[0105] Further, in the embodiment shown in Table 6, the above-mentioned limitation conditions include the limitation of the crude oil processing parameters of the atmospheric and vacuum distillation unit.

[0106] Table 7 Limitation Table of Crude Oil Property Parameters of Atmospheric and Vacuum Distillation Unit

[0107] Name of Crude Oil Property Parameter 1# Atmospheric and Vacuum Distillation 3# Atmospheric and Vacuum Distillation 4# Atmospheric and Vacuum Distillation Upper Limit of Density (tons per cubic meter) 0.9 0.9 0.9 Lower Limit of Density (tons per cubic meter) 0.84 0.84 0.84 Upper Limit of Sulfur Content (mg / kg) 3 3 3 Lower Limit of Sulfur Content (mg / kg) 0 0 0 Upper Limit of Acid Value (mgKOH / g) 0.5 0.5 2 Lower Limit of Acid Value (mgKOH / g) 0 0 0

[0108] Further, in the embodiment shown in Table 7, the above-mentioned limitation conditions include the limitation of the mixed crude oil property parameters of the atmospheric and vacuum distillation unit.

[0109] Table 8 Limitation Table of Side Stream Yield Parameters of Atmospheric and Vacuum Distillation Unit

[0110]

[0111]

[0112] Further, in the embodiment shown in Table 8, the above-mentioned limitation information includes the limitation of the side stream yield parameters of the atmospheric and vacuum distillation unit.

[0113] After that, the determination device can establish an optimization model for crude oil scheduling of the atmospheric and vacuum distillation unit according to the above initial information and constraints. Here, the first optimization objective of the crude oil scheduling optimization model includes minimizing the number of production state switches of the atmospheric and vacuum distillation unit under the premise of meeting the constraints.

[0114] Specifically, the determination device can first define the variables of the crude oil scheduling optimization model according to the initial information. Here, the variables in the crude oil scheduling optimization model include at least one of the number of days in the cycle of the crude oil scheduling task, the number of vessels, the number of atmospheric and vacuum distillation units, the number of residue types, the basic properties of oil types, the number of oil types, and the number of side product types.

[0115] Furthermore, in some embodiments, the number of days \(t\in T\), the set is \(T\), and the individual is \(t\), representing the \(t\)-th day in the cycle. The number of vessels \(i\in I\), the set is \(I\), and the individual is \(i\), representing the \(i\)-th vessel. The number of atmospheric and vacuum distillation units \(m\in M\), the set is \(M\), and the individual is \(m\), representing the \(m\)-th atmospheric and vacuum distillation unit. The number of residue types \(n\in N\), the set is \(N\), and the individual is \(n\), representing the \(n\)-th residue type, where \(n = 1\) is coking feedstock, \(n = 2\) is catalytic feedstock, \(n = 3\) is asphalt feedstock, and \(n = 4\) is residue addition feedstock. The basic properties of oil types \(l\in L\), the set is \(L\), and the individual is \(l\), representing the \(l\)-th basic property of oil types, where \(l = 1\) is density, \(l = 2\) is sulfur content, and \(l = 3\) is acid value. The number of oil types \(j\in J\), the set is \(J\), and the individual is \(j\), representing the \(j\)-th oil type. The number of side product types \(y\in Y\), the set is \(Y\), and the individual is \(y\), representing the \(y\)-th side product of the crude oil, where \(y = 1\) is naphtha, \(y = 2\) is the first normal side stream, \(y = 3\) is diesel, \(y = 4\) is wax oil, \(y = 5\) is washing oil, and \(y = 6\) is residue).

[0116] After that, the determination device can determine the optimization objective function of the crude oil scheduling optimization model according to the first optimization objective.

[0117] Furthermore, in some embodiments, the optimization objective function is:

[0118]

[0119] where \(VD\) m,t is the total received amount received by the \(m\)-th atmospheric and vacuum distillation unit from the vessel on the \(t\)-th day, and \(OilChange\) m,t is used to indicate whether the production state of the \(m\)-th atmospheric and vacuum distillation unit changes on the \(t\)-th day.

[0120] Here, if the production state of the atmospheric and vacuum distillation unit changes, the value of \(OilChange\) m,t is 1. Conversely, if the production state of the atmospheric and vacuum distillation unit does not change, the value of \(OilChange\) m,t is 0. Thus, the optimal objective value of the above optimization objective function is determined by the total amount of atmospheric and vacuum crude oil received \(\sum\) as large as possible.m,t VD m,t and the minimum number of production state switches ∑ m, t OilChange m,t are jointly determined.

[0121] Specifically, in some embodiments, specifically, OilChange m,t can be defined as:

[0122]

[0123] where CrudeTankChange j,m,t represents whether the plan of delivering oil type j to the m-th atmospheric and vacuum distillation unit on the t-th day has switched. When there is a switch, the value of CrudeTankChange j,m,t is 1, otherwise the value of CrudeTankChange j,m,t is 0. ReTankChange m,n,t represents whether the plan of the m-th atmospheric and vacuum distillation unit producing the n-th residue oil on the t-th day has switched. When there is a switch, the value of ResTankChange m,n,t is 1, otherwise the value of ResTankChange m,n,t is 0. Any value of ResTankChange j,m,t and ResTankChange m,n,t being 1 is regarded as a switch in the production state of the atmospheric and vacuum distillation unit.

[0124] Furthermore, in some embodiments, ResTankChange j,m,t is subject to the following restrictions:

[0125]

[0126] where XT j,m,t represents whether oil type j is delivered to the m-th atmospheric and vacuum distillation unit on the t-th day. When it is delivered, the value of XT j,m,t is 1, otherwise the value of XT j,m,t is 0. Here, the above multiple inequalities ensure that if the crude oil delivery plans for two adjacent days are the same, that is, when the values of XT j,m,t and XT j,m,t-1 are the same, the value of CrudeTankChange j,m,t is 0. Conversely, if the crude oil delivery plans for two adjacent days are different, the value of CrudeTankChange j,m,t is 1.

[0127] Similarly, in some embodiments, ResTankChangem,n,t Subject to the following restrictions:

[0128]

[0129] Among them, XC m,n,t indicates whether the mth atmospheric and vacuum distillation unit produces the nth type of residue oil on the tth day. When producing, the value of XC m,n,t is 1, and conversely, the value of XC m,n,t is 0. Here, the above-mentioned multiple inequalities ensure that if the crude oil production plans for two adjacent days are the same, that is, when the values of XC m,n,t and XC m,n,t-1 are the same, the value of ResTankChange m,n,t is 0. Conversely, if the crude oil production plans for two adjacent days are different, the value of ResTankChange m,n,t is 1.

[0130] After that, the determination device can establish the constraint conditions of the crude oil scheduling optimization model according to the obtained various constraint conditions.

[0131] Here, in order to avoid the optimization process of the crude oil scheduling plan from being too complex, the above-mentioned method for determining the crude oil scheduling plan provided by the first aspect of the present invention can convert and organize the component oils stored in the physical tank into virtual tank inventories for separately storing various oil types. Correspondingly, the above-mentioned method for determining the crude oil scheduling plan can count the virtual tank inventories of various sulfur-containing wax oils, low-sulfur wax oils, and various residue oils. For various wax residue oils, there are upper and lower limits on inventory, fixed output, and fixed consumption values according to actual production requirements.

[0132] Furthermore, in some embodiments, the determination device can first determine the inventory value of the crude oil virtual tank every day:

[0133]

[0134] Among them, WJ j,t represents the virtual tank inventory of oil type j on the tth day. WV i,j,t represents the amount of oil type j unloaded by the ith ship on the tth day. VT j,m,t represents the amount of oil type j transported to the mth atmospheric and vacuum distillation unit on the tth day.

[0135] Specifically, due to the limitations of the processing capacity of the atmospheric and vacuum distillation unit, the determination device needs to consider the limit of the atmospheric and vacuum processing volume, and at the same time make the atmospheric and vacuum distillation unit operate at full load as much as possible. Therefore, the processing volume of the atmospheric and vacuum distillation unit needs to be controlled within the upper and lower limits and approach the upper limit for processing production.

[0136] After that, the determination device can determine the upper and lower limits of the total processing volume processed by the atmospheric and vacuum distillation unit every day to limit the total processing volume.

[0137] Specifically, the daily crude oil delivery volume VT from the virtual crude oil tank to the atmospheric and vacuum distillation unit j,m,t needs to be balanced with the total daily processing volume VD of the atmospheric and vacuum distillation unit m，t to maintain material balance:

[0138]

[0139] After that, it is determined that the device can limit the upper and lower limits of the total daily crude oil processing volume VD of the atmospheric and vacuum distillation unit m,t :

[0140]

[0141] Among them, FDmin m represents the lower limit of the total daily crude oil processing volume of the m-th atmospheric and vacuum distillation unit, and FDmax m represents the upper limit of the total daily crude oil processing volume of the m-th atmospheric and vacuum distillation unit.

[0142] After that, it is determined that the device can determine the upper limit of the processing ratio when each atmospheric and vacuum distillation unit processes various oil types to produce corresponding types of residue oil according to the total crude oil volume VD m,t , and the crude oil volume VT input into the atmospheric and vacuum distillation unit j,m,t :

[0143] If XC m,n,t = 1

[0144] Among them, PJ j,n represents the upper limit of the processing volume ratio of the j-th crude oil to produce the n-th residue oil in the total processing volume of the atmospheric and vacuum distillation unit. Here, this constraint condition only considers the type of residue oil n determined to be produced by the m-th atmospheric and vacuum distillation unit on the t-th day, and does not consider other types of residue oil, that is, only considered when XC m,n,t = 1.

[0145] Similarly, it is determined that the device can also determine the upper and lower limits of the mixing properties when each atmospheric and vacuum distillation unit processes the basic properties of various oil types according to the total crude oil volume VD m,t , and the crude oil volume VT input into the atmospheric and vacuum distillation unit j,m,t :

[0146]

[0147] Among them, Pmin m,l represents the lower limit of the l-th mixing property of the m-th atmospheric and vacuum distillation unit, Pmax m,l represents the upper limit of the l-th mixing property of the m-th atmospheric and vacuum distillation unit, and P j,l represents the l-th property value of the j-th oil.

[0148] After that, the determination device can determine the upper limit of the production of slag feedstock when the atmospheric and vacuum distillation unit processes various oil types based on the daily crude oil input to the atmospheric and vacuum distillation unit, the side stream output ratio when the atmospheric and vacuum distillation unit processes various oil types to produce corresponding types of residue, and the amount of residue oil produced when the atmospheric and vacuum distillation unit produces slag feedstock:

[0149] If XC m,n＝4,t = 1

[0150] wherein, FCY j,m,y＝6 represents the side stream output ratio of residue oil when the m-th atmospheric and vacuum distillation unit processes oil type j, VCN m,n＝4,t represents the amount of residue oil produced when the m-th atmospheric and vacuum distillation unit produces slag feedstock on the t-th day, PN j represents the upper limit of the processing amount of oil type j as a proportion of the total processing amount of the atmospheric and vacuum distillation unit when producing slag feedstock. Here, this constraint condition is only considered when the atmospheric and vacuum distillation unit produces slag feedstock, that is, only considered when XC m,n＝4,t = 1.

[0151] After that, the determination device can determine the upper and lower limits of the daily side stream output of each atmospheric and vacuum distillation unit, and limit the daily side stream output of each atmospheric and vacuum distillation unit according to the daily crude oil input VT j,m,t to each atmospheric and vacuum distillation unit:

[0152]

[0153] wherein, FCYmin m,y represents the daily output lower limit of the y-th side stream product of the m-th atmospheric and vacuum distillation unit, and FCYmax m,y represents the daily output upper limit of the y-th side stream product of the m-th atmospheric and vacuum distillation unit.

[0154] After that, the determination device can determine the upper and lower limits of the daily inventory value of each residue oil virtual tank to limit the daily inventory value of each residue oil virtual tank.

[0155] Specifically, the determination device can first determine the daily inventory value of each residue oil virtual tank:

[0156]

[0157] wherein, WR n,t represents the inventory value of the virtual tank of the n-th residue oil on the t-th day, VRyield n represents the fixed output value of the n-th residue oil per day, and VRconsu n represents other fixed consumption values of the n-th residue oil per day.

[0158] After that, the determination device can determine the upper and lower limits of the daily inventory value of each residue oil virtual tank:

[0159]

[0160] Among them, WRmin n represents the lower limit of the virtual tank inventory of the nth residue oil, and WRmax n represents the upper limit of the virtual tank inventory of the nth residue oil.

[0161] After that, the determining device can determine the upper and lower limits of the daily inventory value of the sulfur-containing wax oil virtual tank to limit the daily inventory value of the sulfur-containing wax oil virtual tank.

[0162] Specifically, the determining device can determine the daily inventory value of the sulfur-containing wax oil virtual tank:

[0163]

[0164] Among them, WWS t represents the inventory value of the sulfur-containing wax oil virtual tank on the tth day, VCNW m,n,t represents the amount of wax oil produced when the mth atmospheric and vacuum distillation unit produces the nth residue oil on the tth day, WWSyield represents the fixed daily output of the sulfur-containing wax oil virtual tank, and WWSconsu represents the fixed daily consumption of the sulfur-containing wax oil virtual tank.

[0165] After that, the determining device can determine the upper and lower limits of the daily inventory of the sulfur-containing wax oil virtual tank:

[0166]

[0167] Among them, WWSmin represents the lower limit of the inventory of the sulfur-containing wax oil virtual tank, and WWSmax represents the upper limit of the inventory of the sulfur-containing wax oil virtual tank.

[0168] Similarly, the determining device can determine the upper and lower limits of the daily inventory value of the low-sulfur wax oil virtual tank to limit the daily inventory value of the low-sulfur wax oil virtual tank.

[0169] Specifically, the determining device can determine the inventory value of the low-sulfur wax oil virtual tank:

[0170]

[0171] Among them, WWLS t represents the inventory value of the low-sulfur wax oil virtual tank on the tth day, WWLSyield represents the fixed daily output of the low-sulfur wax oil virtual tank, and WWLSyconsu represents the fixed daily consumption of the low-sulfur wax oil virtual tank.

[0172] After that, the determining device can determine the upper and lower limits of the daily inventory of the low-sulfur wax oil virtual tank:

[0173]

[0174] Among them, WWLSymin represents the lower inventory limit of the low-sulfur wax oil virtual tank, and WWLSmax represents the upper inventory limit of the low-sulfur wax oil virtual tank.

[0175] After that, the determination device can determine the upper and lower limits of the proportions of the light oil amount and the heavy oil amount processed by each atmospheric and vacuum distillation unit per day in the total processing amount according to the amount of crude oil input into the atmospheric and vacuum distillation unit every day and the total processing amount processed by the atmospheric and vacuum distillation unit every day, so as to limit the proportions of the light oil amount and the heavy oil amount in the total processing amount.

[0176] Specifically, the determination device can determine the upper and lower limits of the proportion of the light oil amount processed by each atmospheric and vacuum distillation unit per day in the total processing amount:

[0177]

[0178] Among them, LOmin m,t represents the lower limit of the proportion of the light oil amount processed by the m-th atmospheric and vacuum distillation unit on the t-th day, and LOmax m,t represents the upper limit of the proportion of the light oil amount processed by the m-th atmospheric and vacuum distillation unit on the t-th day, and j ∈ LO indicates that the oil type j is taken from the light oil set LO.

[0179] Similarly, the determination device can determine the upper and lower limits of the proportion of the heavy oil amount processed by each atmospheric and vacuum distillation unit per day in the total processing amount:

[0180]

[0181] Among them, HOmin m,t represents the lower limit of the proportion of the heavy oil amount processed by the m-th atmospheric and vacuum distillation unit on the t-th day, and HOmax m,t represents the upper limit of the proportion of the heavy oil amount processed by the m-th atmospheric and vacuum distillation unit on the t-th day, and j ∈ HO indicates that the oil type j is taken from the heavy oil set HO.

[0182] After that, the determination device can limit the types of residual oil produced by each atmospheric and vacuum distillation unit every day.

[0183] Specifically, the determination device limits each atmospheric and vacuum distillation unit to produce only one type of residual oil every day:

[0184]

[0185] For specific details, please further refer to Figure 3 . Figure 3 The figure shows a schematic flow chart for solving the crude oil scheduling optimization model provided according to some embodiments of the present invention.

[0186] After that, it is determined that the device can input the initial information and the limiting conditions into the crude oil scheduling optimization model and solve it to obtain the corresponding crude oil scheduling plan.

[0187] Specifically, as Figure 3 shown, it is determined that the device can first obtain the population size and the maximum number of evolutions of the crude oil scheduling optimization model.

[0188] After that, it is determined that the device can, in the outer loop, determine the initial switching times of the production status of the atmospheric and vacuum distillation units according to the initial information.

[0189] Furthermore, in some embodiments, it is determined that the device can first determine the maximum value CNmax of the switching times of the production status of the atmospheric and vacuum distillation units:

[0190] CNmax = m max ·(t max - 1) + 1

[0191] where m max is the number of atmospheric and vacuum distillation units, and t max is the number of days in the cycle of the crude oil scheduling task.

[0192] After that, it is determined that the device can determine the initial switching times of the production status of the atmospheric and vacuum distillation units:

[0193]

[0194] where cn is the initial switching times of the production status of the atmospheric and vacuum distillation units.

[0195] Here, the initial switching times determined in the outer loop are used as an important parameter for initializing individuals in the inner loop to complete the initialization of individuals and obtain the initial population. Optimizing the population to obtain a feasible and better solution can reduce the switching times in the outer loop, and conversely, increase the switching times in the outer loop.

[0196] Please refer to Figure 4 . Figure 4 shows a decision variable coding diagram provided according to some embodiments of the present invention.

[0197] After that, as Figure 4 shown, it is determined that the device can, in the inner loop, determine a plurality of initialized individuals according to the initial switching times cn, the first optimization objective, and the second optimization objective. Here, the second optimization objective includes maximizing the operating load of the atmospheric and vacuum distillation units on the premise of meeting the limiting conditions.

[0198] Furthermore, in some preferred embodiments, it is determined that the device can first determine each initialized individual:

[0199] COPP k = [CNk , RANDP k , k ∈ {1, 2, …, Np}

[0200] Among them, COPP k is the k-th initialized individual, which is a row vector with a dimension of cn + (1 + OilNum max ·2)·(cn + m max ). OilNum max is the maximum number of oil types delivered to the atmospheric and vacuum distillation unit, and Np is the population size.

[0201] After that, the determining device can determine multiple random time nodes and multiple production plans for each initialized individual:

[0202] CN k = {rand 1 , rand 2 , …, rand cn}

[0203]

[0204] Among them, CN k is the first cn dimensions of the k-th initialized individual, which is used to represent the random time node rand at which the production state of the k-th initialized individual's atmospheric and vacuum distillation unit switches, and the number of random time nodes is cn. RANDP k is the last (1 + OilNum max ·2)·(cn + m max ) dimensions of the k-th initialized individual, which is used to represent the production plan plan. The number of production plans is (cn + m max ), and its subscript represents the plan serial number. The first dimension of each plan is a random value of the produced residue oil type, and the subsequent OilNum max dimensions are random values of the processed oil type numbers, and the subsequent OilNum max dimensions are random values of the corresponding oil type processing amounts.

[0205] After that, the determining device can determine the individual coding method for each initialized individual according to the population size, the maximum number of evolutions, and the variables of the crude oil scheduling optimization model, so as to obtain the initialized population.

[0206] Please refer further to Figure 5 . Figure 5 shows the result graph of the optimization of the crude oil scheduling plan provided according to some embodiments of the present invention.

[0207] After that, as Figure 5 shown, the determining device can optimize the initialized population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan.

[0208] Specifically, in the process of optimizing the initial population, the determining device can define each population individual as a target vector, and generate a mutation vector of each population individual according to each target vector, the initially set scaling factor, and the preset mutation strategy. Herein, the mutation strategy is to randomly select a certain number of individuals in the population that are different from the target vector, and generate the mutation vector of each said population individual according to a preset calculation formula.

[0209] Further, in some embodiments, each initialization individual in each generation is sequentially used as the target vector X q,g , and two corresponding individuals are randomly selected and to obtain the corresponding mutation vector V q,g :

[0210]

[0211] g ∈ 1, …, G, q ∈ 1, …, Np

[0212] wherein is randomly obtained from the above-mentioned initial population, is randomly obtained from the union of the above-mentioned initial population and the external storage set A. F q,g represents the scaling factor when the q-th initialization individual in the g-th generation is used as the target vector, and it is a random number that conforms to the Cauchy distribution C(μ F , 0.1) and is restricted within (0, 1]. represents a random individual in the set of the first beforeP·Np initialization individuals in the g-th generation, and beforeP is an adjustable value within the range of [2 / Np, 0.2], and its lower limit ensures that at least the first two most excellent individuals participate in the random selection.

[0213] After that, the determining device can generate a trial vector of each population individual according to the above-mentioned target vector, mutation vector, the initially set crossover probability, and the preset recombination rule. Herein, the recombination rule is that each element at each position of the target vector has a certain probability of being replaced by the corresponding element at the position of the mutation vector.

[0214] Further, in some embodiments, the determining device can obtain the trial vector u q,g when the q-th individual in the g-th generation is used as the target vector:

[0215]

[0216] wherein s represents the s-th element in the individual coding, and rand q,s [0, 1] represents a random value between 0 and 1, and rand s[0,S] represents a random integer value from 0 to S, and cr q,g represents the crossover probability when the q-th individual in the g-th generation is used as the target vector, which is a random number that conforms to the normal distribution N(μ Cr , 0.1) and is restricted within [0, 1].

[0217] After that, the determination device can determine the selection rules for various population individuals and compare the trial vector with the target vector.

[0218] Furthermore, during the process of comparing the trial vector with the target vector, the following rules should be followed:

[0219] (1) A feasible solution is always better than an infeasible solution;

[0220] (2) When both are feasible solutions, select the individual with a better objective function value; and

[0221] (3) When both are infeasible solutions, select the individual with less constraint violation.

[0222] After that, the determination device can ensure the above rules for selecting the best individuals in the population based on the following formula:

[0223]

[0224] where x 1 and x 2 represent two different initialized individuals, obj(x 1 ) and obj(x 2 ) represent the objective values of two different initialized individuals, and VOC(x 1 ) and VOC(x 2 ) represent the degrees of constraint violation of two different initialized individuals. Here, the fitness of individual x 1 is better than that of individual x 2 .

[0225] After that, in response to the trial vector being better than the target vector, the determination device can update the scaling factor and the crossover probability to obtain the corresponding crude oil scheduling plan.

[0226] Specifically, after updating the scaling factor and crossover probability, the population in the inner loop enters the next generation, and the determining device can continue to search for individuals that meet the constraint conditions until the maximum number of iterations or an individual that meets the constraint conditions is found and the inner loop is exited. After that, in the outer loop, the determining device can proceed to the next step based on the result of the ended inner loop. If the inner loop finds an individual that meets the constraint conditions, it continues to reduce the switching times of the production state of the atmospheric and vacuum distillation unit and enters the inner loop. If no individual that meets the constraint conditions is found, it determines that the switching times of the production state of the atmospheric and vacuum distillation unit determined in the previous outer loop are the minimum switching times, and the found individual is the crude oil scheduling plan with the minimum switching times of the production state of the atmospheric and vacuum distillation unit. In this way, the determining device can search for the population individuals that meet the constraint conditions in the inner and outer loops to obtain the corresponding crude oil scheduling plan.

[0227] Further, in some embodiments, for the case where the trial vector in each generation successfully outperforms the target vector, the determining device can set the scaling factor F q,g recorded in the contemporary successful scaling factor set S F and the crossover probability Cr q,g recorded in the contemporary successful crossover probability set S Cr At the beginning of each generation of optimization, the records in the sets S F and S Cr are cleared.

[0228] After that, the determining device can define the successful parameter historical information sets and The capacities of the two sets are equal and both are adjustable values less than the population size, denoted as H. All H elements in the set are adjustable default values. When replacing the target vector in each generation, a random value r q is taken again, r q ∈1, 2, …, H. Furthermore, let the successful parameter historical information and represent the r -th element in the set q when the q-th individual is the target vector, and represent the r -th element in the set q when the q-th individual is the target vector;

[0229] After that, the determining device can define the update pointer key of the successful parameter historical information set, with an initial value of 1. The value of key increases with the increase of the generation number, increasing by 1 each time. When reaching the capacity upper limit H, it will be reset to 1 in the next generation, and so on. After all individuals in each generation complete mutation, recombination, and selection, the values of and are updated. Represents the key-th element of the set , Represents the key-th element of the set .

[0230] Herein, the update rule of

[0231]

[0232] Δf a =|obj(u q,g ) - obj(X q,g )|

[0233] wherein, represents the value of the key-th element in the set at the g-th generation. If then the value of the next generation is updated to mean WL (S F ), otherwise the value is not updated.

[0234] Similarly, the update rule of

[0235]

[0236] Δf a =|obj(u q,g ) - obj(X q,g )|

[0237] wherein, represents the value of the key-th element in the set at the g-th generation. If then the value of the next generation is updated to mean WA (S Cr ), otherwise the value is not updated.

[0238] In addition, in some preferred embodiments, in response to the trial vector being superior to the target vector, the determining device may define an external storage set A and store the replaced target vector in the external storage set A. When the number of individuals stored in the external storage set A reaches the upper limit, the newly deposited individual will replace a random individual in the external storage set A. Thus, the above-mentioned method for determining the crude oil scheduling scheme provided by the first aspect of the present invention can ensure the diversity of population individuals.

[0239] Such as Figure 5As shown, the optimal number of switches obtained by the method for determining the above crude oil scheduling plan provided by the first aspect of the present invention is 2 times. The optimized crude oil scheduling plan is very close to the daily production plan of the refinery, and greatly reduces the production scheduling time and labor costs.

[0240] In summary, the method for determining the above crude oil scheduling plan, the device for determining the crude oil scheduling plan, and the computer-readable storage medium provided by the present invention can all solve the crude oil scheduling optimization model established according to the actual working conditions by using the adaptive differential evolution algorithm, so as to obtain a crude oil scheduling plan that conforms to the actual processing conditions, thereby reducing the production scheduling cost in the crude oil refining process and improving the production scheduling efficiency in the crude oil refining process.

[0241] 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 that are illustrated and described herein or that are not illustrated and described herein but are understood by those skilled in the art.

[0242] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, 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 the processor such that the processor can read from and write to the storage medium. In an alternative, the storage medium may be integrated into the 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 as discrete components in the user terminal.

[0243] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code. The computer-readable medium includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. The storage media may be any available media that can be accessed by a computer. By way of example and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a web site, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, the disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc where the disk typically reproduces the data magnetically, while the disc reproduces the data optically with a laser. Combinations of the above should also be included within the scope of computer-readable media.

[0244] The foregoing description of the disclosure has been provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic 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 is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a crude oil scheduling plan, characterized in that: The following steps are involved: Obtain initial information and constraints in the crude oil scheduling process; According to the initial information and the constraint conditions, a crude oil scheduling optimization model of the atmospheric and vacuum distillation unit is established, wherein a first optimization objective of the crude oil scheduling optimization model includes: minimizing the number of production state switching times of the atmospheric and vacuum distillation unit under the premise of satisfying the constraint conditions; and The initial information and the restriction conditions are input into the crude oil scheduling optimization model, and the model is solved to obtain a corresponding crude oil scheduling solution.

2. The determination method according to claim 1, characterized in that: The initial information includes the period of the crude oil scheduling task, the arrival date of the ship within the period, the type and quality of the crude oil transported by the ship, the oil distribution of the crude oil storage tank group, the initial storage capacity, crude oil storage tank information, the initial storage capacity of the wax residue oil storage tank, the fixed production value and fixed consumption value of the wax residue oil, at least one of the properties and yield of the crude oil, and / or The restriction conditions include at least one of the crude oil processing parameter restriction, the mixed crude oil property parameter restriction, and the side line production parameter restriction of the atmospheric and vacuum distillation unit.

3. The determination method according to claim 2, characterized in that: The step of establishing the crude oil scheduling optimization model of the atmospheric and vacuum distillation unit according to the initial information and the restriction conditions comprises: According to the initial information, defining variables of the crude oil scheduling optimization model; Determining an optimization objective function of the crude oil scheduling optimization model according to the first optimization objective; and According to the obtained restriction conditions, the restriction conditions of the crude oil scheduling optimization model are established.

4. The determination method according to claim 3, characterized in that: The variables include at least one of the number of days in the cycle of the crude oil scheduling task, the number of the ships, the number of the atmospheric and vacuum distillation units, the number of residual oil types, the basic properties of oil types, the number of oil types, and the number of sideline product types.

5. The determination method according to claim 3, characterized in that: The optimization objective function is: Among them, VD m,t is the total volume received by the mth atmospheric and vacuum unit from the crude oil storage tank on the tth day, OilChange m,t Used to indicate whether the production status of the mth constant and distillation unit on the tth day has been switched.

6. The determination method according to claim 5, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions includes: Determine the daily inventory value of the crude oil virtual tank: Among them, WJ j,t is the virtual tank inventory of oil type j on day t, WV i,j,t is the amount of oil type j unloaded by the i-th ship on day t, VT j,m,t is the amount of oil type j delivered to the mth atmospheric and vacuum distillation unit on the tth day; According to the crude oil input amount from the crude oil virtual tank to the atmospheric and vacuum device, the total processing amount of the atmospheric and vacuum device per day is determined: Among them, VT j,m,t is the amount of oil type j delivered to the mth atmospheric and vacuum distillation unit on day t; and Determine the upper and lower limits of the total processing volume processed by the atmospheric and vacuum distillation device every day to limit the total processing volume: Among them, FDmin m FDmax is the lower limit of the total processing volume of the mth atmospheric and vacuum unit per day. m It is the upper limit of the total processing volume of the mth atmospheric and vacuum distillation unit per day.

7. The determination method according to claim 6, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions also includes: According to the total processing volume and the input crude oil volume, the upper limit of the processing ratio of each of the atmospheric and vacuum distillation units when processing various oil types to generate corresponding types of residual oil is determined: If XC m,n,t =1 Among them, PJ j,n The upper limit of the ratio of the processing volume of the j-th crude oil to the total processing volume of the atmospheric and vacuum unit when producing the n-th residual oil, XC m,n,t =1 means that the mth atmospheric and vacuum unit produces the nth type of residual oil on the tth day, XC m,n,t =0 means that the mth atmospheric and vacuum unit does not produce the nth type of residual oil on the tth day; According to the total processing volume and the input crude oil volume, the upper and lower limits of the mixed properties of each of the atmospheric and vacuum distillation devices when processing oils of various basic properties of oils are determined: Among them, Pmin m,l is the lower limit of the lth mixed property of the mth atmospheric and vacuum device, Pmax m,l is the upper limit of the lth mixed property of the mth atmospheric and vacuum device, P j,l is the lth attribute value of the jth oil; According to the input crude oil amount, the sideline output ratio of the atmospheric and vacuum device when processing various oil types to generate corresponding types of residual oil, and the amount of residual oil produced when the atmospheric and vacuum device produces residual feed, the upper limit of the production residual feed when the atmospheric and vacuum device processes various oil types is determined: If XC m,n＝4,t =1 Among them, FCY j,m,y＝6 VCN is the sideline output ratio of residual oil when the mth atmospheric and vacuum unit processes oil type j, m,n＝4,t is the amount of residual oil produced when the mth atmospheric and vacuum unit produces the residue feed on the tth day, PN j The upper limit of the proportion of the processing volume of oil type j to the total processing volume of the atmospheric and vacuum distillation unit when producing the slag feed; and Determine the upper and lower limits of the daily sideline output of each of the atmospheric and vacuum devices, and limit the daily sideline output of each of the atmospheric and vacuum devices according to the amount of crude oil input into the atmospheric and vacuum devices every day: Among them, FCYmin m,y is the daily output lower limit of the yth side product of the mth atmospheric and vacuum unit, FCYmax m,y It is the upper limit of daily output of the yth side-line product of the mth atmospheric and vacuum distillation unit.

8. The determination method according to claim 6, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions also includes: Determine the daily inventory value of each residual oil virtual tank: Among them, WR n,t is the virtual tank inventory value of the nth type of residual oil on the tth day, VRyield n is the fixed output value of the nth type of residual oil per day, VRcons n Other fixed daily consumption values ​​for the nth type of residual oil; and Determine the upper and lower limits of the daily inventory value of each of the residual oil virtual tanks to limit the daily inventory value of each of the residual oil virtual tanks: Among them, WRmin n is the lower limit of the virtual tank inventory of the nth type of residual oil, WRmax n It is the upper limit of virtual tank inventory of the nth type of residual oil.

9. The determination method according to claim 6, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions also includes: Determine the daily inventory value of the sulfur-containing wax oil virtual tank: Among them, WWS t is the inventory value of the virtual tank of sulfur-containing wax oil on day t, VCNW m,n,t is the amount of wax oil produced when the mth atmospheric and vacuum unit produces the nth type of residual oil on the tth day, WWSyield is the fixed output of the sulfur-containing wax oil virtual tank per day, and WWSconsu is the fixed consumption of the sulfur-containing wax oil virtual tank per day; and Determine the upper and lower limits of the daily inventory value of the sulfur-containing wax oil virtual tank to limit the daily inventory value of the sulfur-containing wax oil virtual tank: Among them, WWSmin is the lower limit of the inventory of the virtual tank containing sulfur wax oil, and WWSmax is the upper limit of the inventory of the virtual tank containing sulfur wax oil.

10. The determination method according to claim 6, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions also includes: Determine the inventory value of the low sulfur gas oil virtual tank: Among them, WWLS t is the inventory value of the low-sulfur wax oil virtual tank on day t, WWLSyield is the fixed daily output of the low-sulfur wax oil virtual tank, and WWLSconsu is the fixed daily consumption of the low-sulfur wax oil virtual tank; and Determine the upper and lower limits of the daily inventory value of the low-sulfur wax oil virtual tank to limit the daily inventory value of the low-sulfur wax oil virtual tank: Among them, WWLSmin is the lower limit of the inventory of the low-sulfur wax oil virtual tank, and WWLSmax is the upper limit of the inventory of the low-sulfur wax oil virtual tank.

11. The determination method according to claim 6, characterized in that: The step of establishing the constraint conditions of the crude oil scheduling optimization model according to the obtained constraint conditions also includes: According to the amount of crude oil input into the atmospheric and vacuum devices every day and the total processing volume processed by the atmospheric and vacuum devices every day, the upper and lower limits of the proportion of the amount of light oil processed by each atmospheric and vacuum devices every day to the total processing volume are determined to limit the proportion of the amount of light oil to the total processing volume: Among them, LOmin m,t LOmax is the lower limit of the proportion of light oil processed by the mth atmospheric and vacuum unit on the tth day. m,t is the upper limit of the proportion of light oil processed by the mth atmospheric and vacuum unit on the tth day, LO is the light oil collection; According to the amount of crude oil input into the atmospheric and vacuum devices every day and the total processing volume processed by the atmospheric and vacuum devices every day, the upper and lower limits of the proportion of the heavy oil volume processed by each atmospheric and vacuum devices every day to the total processing volume are determined to limit the proportion of the heavy oil volume to the total processing volume: Among them, HOmin m,t HOmax is the lower limit of the proportion of heavy oil processed by the mth atmospheric and vacuum unit on the tth day. m,t is the upper limit of the proportion of heavy oil processed by the mth atmospheric and vacuum unit on the tth day, HO is the heavy oil aggregate; and The types of residual oil produced daily by each of the atmospheric and vacuum units are limited as follows: Among them, XC m,n,t =1 means that on the tth day, the mth atmospheric and vacuum distillation unit produces the nth type of residual oil.

12. The determination method according to claim 3, characterized in that: The step of inputting the initial information and the restriction conditions into the crude oil scheduling optimization model and solving the model to obtain the corresponding crude oil scheduling solution includes: Obtaining the population size and maximum number of evolutions of the crude oil scheduling optimization model; In the outer cycle, the initial switching times of the production state of the atmospheric and vacuum distillation device are determined according to the initial information; In the inner loop, a plurality of initialization individuals are determined according to the initial switching times, the first optimization target and the second optimization target, wherein the second optimization target includes: maximizing the operating load of the atmospheric and vacuum distillation device under the premise of satisfying the restriction condition; Determining the individual encoding method of each of the initialized individuals according to the population size, the maximum number of evolutions, and the variables of the crude oil scheduling optimization model to obtain an initialized population; and Based on an adaptive differential evolution algorithm, the initialization population is optimized to obtain a corresponding crude oil scheduling solution.

13. The determination method according to claim 12, characterized in that: In the outer cycle, the step of determining the initial switching times of the production state of the atmospheric and vacuum distillation device according to the initial information comprises: Determine the maximum value CNmax of the switching times of the production state of the atmospheric and vacuum distillation device: CNmax=m max ·(t max -1)+1 Among them, m max is the number of the atmospheric and vacuum devices, t max The number of days of the cycle of the crude oil scheduling task; and Determine the initial switching times of the production state of the atmospheric and vacuum distillation device: Wherein, cn is the initial switching number of the production state of the constant pressure reduction device.

14. The determination method according to claim 13, characterized in that: The step of determining a plurality of initialization individuals according to the initial switching number, the first optimization target and the second optimization target comprises: Determine each of the initialization individuals: COPP k =[CN k ,RANDP k ],k∈{1,2,…,Np} Among them, COPP k is the kth initialized individual, whose dimension is cn+(1+OilNum max ·2)·(cn+m max ), OilNum max is the maximum number of oil types delivered to the atmospheric and vacuum distillation unit, Np is the size of the oil type population; and Determine multiple random time nodes and multiple production plans for each of the initialization individuals: CN k ={rand1,rand2,…,rand cn } Among them, CN k The random time node rand used to represent the production state switching of the atmospheric and vacuum distillation device of the kth initialized individual, the number of which is cn, RANDP k It is used to represent the production plan. The number of the production plan is (cn+m max ).

15. The determination method according to claim 14, characterized in that: The step of optimizing the initialization population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan includes: Defining each population individual as a target vector, and generating a mutation vector of each population individual according to each target vector, an initially set scaling factor, and a preset mutation strategy; Generate a test vector for each individual of the population according to the target vector, the mutation vector, an initially set crossover probability, and a preset recombination rule; Determine a selection rule for each of the population individuals, compare the test vector with the target vector; and In response to the trial vector being better than the target vector, the scaling factor and the crossover probability are updated to obtain a corresponding crude oil scheduling solution.

16. The determination method according to claim 14, characterized in that: The step of optimizing the initialization population based on the adaptive differential evolution algorithm to obtain the corresponding crude oil scheduling plan also includes: In response to the trial vector being better than the target vector, an external storage set is defined, and the replaced target vector is stored in the external storage set to ensure the diversity of individuals in the population.

17. A device for determining a crude oil scheduling plan, characterized in that: include: a memory having computer instructions stored thereon; and A processor, connected to the memory, is used to execute computer instructions stored in the storage module to implement the method for determining the crude oil scheduling plan according to any one of claims 1 to 16.

18. 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 determining a crude oil scheduling plan according to any one of claims 1 to 16 is implemented.

Images