Refinery production scheduling optimization method and device

Abstract

The invention discloses a refinery production scheduling optimization method and device. The method comprises the following steps: constructing a refinery production scheduling optimization model based on a refinery production scheduling expert rule and a pre-established refinery production scheduling mathematical model, wherein the production scheduling expert rule is formulated according to the actual production process of the refinery; inputting the actual production parameters of the refinery plant into the refinery plant production scheduling optimization model and solving to obtain a model solving result; and obtaining a refinery production scheduling business result based on a model solving result. According to the method, the production process of the refinery plant can be optimized and scheduled more reasonably and scientifically under the constraint of the production scheduling expert rule, the executability of the production scheduling of the refinery plant is improved, and the working efficiency of the production scheduling and scheduling of the refinery plant is improved.

Description

Technical Field

[0001] This invention relates to the field of production scheduling optimization and production planning technology, and in particular to a refinery production scheduling optimization method and apparatus. Background Technology

[0002] Refinery scheduling is a crucial link between planning and operation in a company's production activities. It requires optimizing and decomposing the company's production plan benefit targets at the scheduling level to form production scheduling plans that are then issued to the workshops for execution. It is the core of the company's production operations. Production scheduling includes activities such as the supply of raw materials for unit processing, the arrangement of unit output materials, and the receipt and dispatch of oil from intermediate material tanks. It is characterized by a wide variety of materials, multiple material flows, and complex connection structures between units and material tanks. Inappropriate scheduling can easily lead to problems such as frequent switching of unit processing schemes, fluctuations in unit load, and full or empty tanks storing intermediate materials.

[0003] Existing research employs operations research techniques to schedule and allocate production in refinery units, enabling refineries to achieve optimal production scheduling with the corresponding feasible solutions. Summary of the Invention

[0004] In existing production scheduling, operations research techniques are often used to achieve optimal production scheduling for refineries. However, this method focuses more on optimizing the scheduling result and does not consider the production and processing process from the perspective of scheduling experts. Optimizing production scheduling solely from the perspective of scheduling results is not scientific enough, as it does not consider whether the actual production and processing process can be executed. This can lead to unreasonable production scheduling arrangements and waste of production resources. Therefore, how to scientifically optimize refinery production scheduling from the perspective of the production and processing process, and improve refinery production efficiency, is an urgent problem to be solved.

[0005] In view of the above problems, the present invention is proposed to provide a refinery production scheduling optimization method and apparatus that overcomes or at least partially solves the above problems.

[0006] In a first aspect, embodiments of the present invention provide a refinery production scheduling optimization method, comprising:

[0007] A refinery production scheduling optimization model is constructed based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the refinery's actual production process.

[0008] Input the actual production parameters of the refinery into the refinery production scheduling optimization model and solve it to obtain the model solution results;

[0009] The refinery production scheduling results are obtained based on the model solution.

[0010] In some optional embodiments, the pre-established mathematical model for refinery production scheduling includes:

[0011] Starting from the refinery's production process, the production optimization objectives and scope are determined based on the refinery's production scheduling objects and production business requirements. The optimization objective function is determined based on the optimization objectives, and the optimization scope refers to the production processes in the refinery that need to be optimized.

[0012] A mathematical model for refinery production scheduling is established based on the optimization scope, refinery production constraints, and optimization objective function.

[0013] In some alternative embodiments, the optimization objective includes: minimizing production costs;

[0014] Production costs include at least one of the following: equipment processing costs, equipment processing scheme switching costs, and material tank storage costs;

[0015] The optimization objective function is expressed as: Minimum cost = Minimum equipment processing cost + Minimum equipment processing scheme switching cost + Minimum material tank storage cost;

[0016] Production constraints include equipment constraints, tank farm constraints, and other constraints;

[0017] The equipment constraints include at least one of the following: the load constraint of the equipment processing scheme, the normalization constraint of the input raw material ratio of the equipment processing scheme, the normalization constraint of the output product yield of the equipment processing scheme, and the input-output material balance constraint of the equipment processing scheme.

[0018] Tank farm constraints include at least one of the following: material tank farm inventory balance constraint, material tank farm and material tank receiving constraint, material tank farm and material tank dispensing constraint, material tank farm and material tank inventory constraint, material tank inventory quantity constraint, and material tank inventory balance constraint.

[0019] Other constraints include at least one of the following: constraints on the amount of raw materials purchased and constraints on the amount of products sold.

[0020] In some optional embodiments, a refinery production scheduling optimization model is constructed based on refinery production scheduling expert rules and a pre-established refinery production scheduling mathematical model, including:

[0021] Add the refinery's production scheduling expert rules to the pre-established production scheduling expert rule library. The production scheduling expert rule library includes at least one of the following: the rule of minimizing unit load fluctuation, the rule of unique unit start-up processing scheme, the rule of asynchronous oil receiving and discharging in material tanks at the same time, the rule of minimizing the number of times material tanks switch continuously receiving oil in the material tank area, and the rule of minimizing the number of times material tanks switch continuously discharging oil in the material tank area.

[0022] The optimization objectives and production constraints in the pre-established refinery production scheduling mathematical model are adjusted based on the production scheduling expert rule base, and a refinery production scheduling optimization model is constructed based on the adjusted optimization objectives and constraints.

[0023] In some optional embodiments, the optimization objective and constraints in a pre-established refinery production scheduling mathematical model are adjusted according to a production scheduling expert rule base, including:

[0024] Based on at least one of the following rules from the production scheduling expert rule base: minimum unit load fluctuation rule, minimum number of switching times for continuous oil receiving material tanks in the material tank area, and minimum number of switching times for continuous oil dispensing material tanks in the material tank area, adjust the optimization objective in the refinery production scheduling mathematical model.

[0025] Adjust the production constraints in the refinery's production scheduling mathematical model based on at least one of the unique rules for device start-up processing schemes and asynchronous rules for oil receipt and payment from material tanks at the same time, from the production scheduling expert rule base.

[0026] In some alternative embodiments, the optimization objective in the refinery production scheduling mathematical model is adjusted, including:

[0027] To minimize unit load fluctuations, the cost of unit load fluctuations is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0028] To minimize the number of switching times between continuous oil receiving tanks in the material tank area, the cost of switching times between continuous oil receiving tanks in the material tank area is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0029] To minimize the number of switching times between continuous oil delivery tanks in the tank farm, the cost of switching times between continuous oil delivery tanks in the tank farm is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0030] Adjust the production constraints in the refinery production scheduling mathematical model, including:

[0031] To address the unique rule for processing schemes at the start of a unit, a constraint condition of mutual exclusion of processing schemes is added to the unit constraints included in the production constraints of the refinery production scheduling mathematical model.

[0032] To address the asynchronous oil receiving and disbursement rules for material tanks at the same time, a mutual exclusion constraint condition for oil receiving and disbursement from material tanks is added to the tank area constraints included in the production constraints of the refinery production scheduling mathematical model.

[0033] In some optional embodiments, a refinery production scheduling optimization model is constructed based on the adjusted optimization objective and constraints, including:

[0034] Based on the adjusted optimization objective, a new optimization objective function is determined; the new objective function is expressed by the following expression: Minimum cost = Minimum processing cost of equipment + Minimum switching cost of equipment processing scheme + Minimum storage cost of material tank + Minimum cost of equipment load fluctuation + Cost of switching times of material tank tank for continuous oil receiving in material tank area + Cost of switching times of material tank tank tank for continuous oil discharging in material tank area.

[0035] Determine new production constraints based on the adjusted production constraints;

[0036] A refinery production scheduling optimization model is constructed based on the optimization scope, the new optimization objective function, and the new production constraints.

[0037] In some optional embodiments, the actual production parameters of the refinery are input into the refinery production scheduling optimization model and solved to obtain the model solution results, including:

[0038] Input the actual production parameters of the refinery into the optimization model, set the solution time and GAP parameters of the optimization model, and use a solver to solve the optimization model to obtain the parameter solution results of the optimization model. The actual production parameters include at least one of the following: optimization cycle, product yield of the unit processing scheme, material tank inventory, raw material purchase plan, product sales plan, and production cost.

[0039] In some optional embodiments, the refinery production scheduling business results are obtained based on the model solution results, including:

[0040] The model solution results are instantiated to obtain the refinery production scheduling business results. The production scheduling business results include at least one of the following: unit input and output information, unit load information, material tank area oil receipt and payment information, material tank inventory information, raw material purchase quantity arrangement information, and product sales arrangement information.

[0041] Secondly, embodiments of the present invention provide a refinery production scheduling optimization device, comprising:

[0042] The optimization model building module is used to construct a refinery production scheduling optimization model based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the refinery's actual production process.

[0043] The optimization model solution module is used to input the actual production parameters of the refinery into the refinery production scheduling optimization model and solve it to obtain the model solution results;

[0044] The business results generation module is used to obtain refinery production scheduling business results based on the model solution results.

[0045] This invention provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned refinery production scheduling optimization method.

[0046] This invention provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a refinery production scheduling optimization method.

[0047] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0048] This invention provides a refinery production scheduling optimization method. Based on refinery production scheduling expert rules and a pre-established refinery production scheduling mathematical model, a refinery production scheduling optimization model is constructed. Typical refinery optimization models only focus on optimizing the model results without considering whether the optimized model results can be obtained through the actual production process. This method considers the production process from the perspective of scheduling experts, scientifically formulates scheduling expert rules, and incorporates these rules into the refinery production scheduling mathematical model. The resulting refinery production scheduling optimization model can more scientifically and accurately optimize the production scheduling process. After establishing the optimization model, the actual production parameters of the refinery are input into the refinery production scheduling optimization model and solved to obtain the model solution results. Based on the model solution results, the refinery production scheduling business results are obtained. After establishing the optimization model, the obtained actual production parameters of the refinery are input into the model for global optimization and solution to obtain the feasible solution of the model. Instantiating the feasible solution yields the refinery production scheduling business results. This method realizes refinery production scheduling optimization and production scheduling according to scheduling expert rules, improving the executability of the production scheduling results.

[0049] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0050] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0051] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0052] Figure 1 This is a flowchart of the refinery production scheduling optimization method in an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of the structure of the refinery production scheduling optimization device in an embodiment of the present invention. Detailed Implementation

[0054] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0055] To address the problems of unscientific and unreasonable refinery production scheduling and low efficiency in existing technologies, this invention provides a refinery production scheduling optimization method.

[0056] This invention provides a refinery production scheduling optimization method, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0057] Step S101: Construct a refinery production scheduling optimization model based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the refinery's actual production process.

[0058] Step S102: Input the actual production parameters of the refinery into the refinery production scheduling optimization model and solve it to obtain the model solution results.

[0059] Step S103: Obtain the refinery production scheduling business results based on the model solution results.

[0060] Refinery production scheduling is a crucial link between planning and operation in a company's production activities. Rational and scientific planning of refinery production scheduling can improve refinery production efficiency. While operations research optimization techniques can achieve optimal production scheduling, there's a problem that this optimized scheduling result cannot be realized through actual production processes. Therefore, this method is not scientifically sound and may lead to unreasonable arrangements. This method, however, considers optimizing the production process from the perspective of scheduling experts to achieve scientifically optimized refinery production scheduling. Scheduling experts are individuals with rich experience and professional knowledge who can formulate and execute effective production scheduling strategies to achieve efficient utilization of refinery resources and efficient task completion. Therefore, a refinery production scheduling optimization model established by incorporating production scheduling expert rules can obtain executable and scientifically effective production scheduling results. Executing the production scheduling plan based on these results can improve refinery production efficiency.

[0061] Optionally, the pre-established mathematical model for refinery production scheduling in step S101 above includes:

[0062] Starting from the refinery's production process, the production optimization objectives and scope are determined based on the refinery's production scheduling objects and production business requirements. The optimization objective function is determined based on the optimization objectives, and the optimization scope refers to the production processes in the refinery that need to be optimized.

[0063] A mathematical model for refinery production scheduling is established based on the optimization scope, refinery production constraints, and optimization objective function.

[0064] Starting from the refinery's production process, based on the refinery's production scheduling objects and production business requirements, it is possible to determine the optimization objectives and optimization processes that need to be optimized. For example, the optimization objective determined in this embodiment is the lowest cost, but the optimization objective can also be the highest production efficiency. A reasonable optimization objective should be determined based on the actual production process. The optimization process is from the atmospheric and vacuum distillation unit to the blending component oil and product storage. Optimization is carried out in this part of the production process.

[0065] Optional optimization objectives include: minimizing production costs;

[0066] Production costs include at least one of the following: equipment processing costs, equipment processing scheme switching costs, and material tank storage costs;

[0067] The optimization objective function is expressed as: Minimum cost = Minimum equipment processing cost + Minimum equipment processing scheme switching cost + Minimum material tank storage cost;

[0068] Production constraints include equipment constraints, tank farm constraints, and other constraints;

[0069] The equipment constraints include at least one of the following: the load constraint of the equipment processing scheme, the normalization constraint of the input raw material ratio of the equipment processing scheme, the normalization constraint of the output product yield of the equipment processing scheme, and the input-output material balance constraint of the equipment processing scheme.

[0070] Tank farm constraints include at least one of the following: material tank farm inventory balance constraint, material tank farm and material tank receiving constraint, material tank farm and material tank dispensing constraint, material tank farm and material tank inventory constraint, material tank inventory quantity constraint, and material tank inventory balance constraint.

[0071] Other constraints include at least one of the following: constraints on the amount of raw materials purchased and constraints on the amount of products sold.

[0072] Specifically, the pre-established mathematical model for refinery production scheduling includes an optimization objective function and constraints. The optimization objective of the refinery production scheduling mathematical model is to minimize costs. Production costs include at least one of the following: unit processing costs, unit processing scheme switching costs, and material tank storage costs. The objective function determined based on the optimization objective can be expressed as: Minimum Cost = Minimum Unit Processing Cost + Minimum Unit Processing Scheme Switching Cost + Minimum Material Tank Storage Cost; the specific expression is as follows:

[0073]

[0074] In formula (1) The processing cost of the production equipment is represented by ∑. t∈T ∑ l∈L (C l,s,s, *X l,s,s,,t ) represents the cost of switching processing schemes for the equipment, ∑ t∈T ∑ j∈J (C j *CINV t,m,j This indicates the cost of storing materials in the tank.

[0075] Specifically, the meaning and specific expressions of the constraints included in the device constraints are as follows:

[0076] The load constraint of the equipment processing plan refers to the range between the minimum and maximum load of the equipment. The specific expression is as follows:

[0077] B l,s,min ≤ ∑ m∈M F l,s,m,t (2)

[0078] ∑ m∈M F l,s,m,t ≤ B l,s,max (3)

[0079] Wherein, formula (2) indicates that the actual load of the production unit processing scheme in cycle t is greater than the corresponding minimum load, ∑ m∈M F l,s,m,t The actual load of the processing scheme of the device is indicated by formula (3), which means that the actual load of the processing scheme of the production device in cycle t is less than the corresponding maximum load.

[0080] The normalization constraint of the input raw material ratio for a processing scheme means that the sum of the proportions of all input raw materials for a given processing scheme is equal to 1. The specific expression is as follows:

[0081] P l,s,m,t = F l,s,m,t / ∑ m∈M F l,s,m,t (4)

[0082] ∑ m∈M P l,s,m,t = 1 (5)

[0083] Formula (4) represents the proportion of the input material quantity of the production device processing scheme s in cycle t to the total input material quantity of the corresponding device processing scheme s, and Formula (5) represents the sum of the proportions of all input materials in the production device processing scheme s in cycle t to be 1.

[0084] The normalization constraint for the product yield of a processing scheme means that the sum of the yields of all products of a given processing scheme equals 1. The specific expression is as follows:

[0085] Y l,s,m,t = D l,s,m,t / ∑ n∈N D l,s,m,t (6)

[0086] ∑ m∈M Y l,s,m,t =1 (7)

[0087] Formula (6) represents the proportion of the output of the production device processing scheme in cycle t to the total output of the corresponding processing scheme, and Formula (7) represents the sum of the yields of all output products in the production device processing scheme in cycle t, which is 1.

[0088] The input-output material balance constraint of a processing unit means that the sum of all input raw material quantities for a given processing unit must equal the sum of output product quantities. The specific expression is as follows:

[0089] ∑ m∈M F l,s,m,t =∑ n∈N D l,s,n,t (8)

[0090] Formula (8) indicates that the total amount of materials input into the production unit processing scheme s in cycle t is equal to the total amount of products output by the corresponding production unit processing scheme s.

[0091] Specifically, the meaning and specific expressions of each constraint condition in the tank farm constraint are as follows:

[0092] The inventory balance constraint for a material tank farm refers to the requirement that the ending inventory of a material tank farm equals the beginning inventory plus the difference between the oil receipts and payments for that material tank farm. The specific expression is as follows:

[0093] CINV t,m,u =CINV t-1,m,u +IQ t,m,u -OQ t,m,u (9)

[0094] Formula (9) indicates that the ending inventory of the material tank area in period t is equal to the beginning inventory plus the difference between the amount of oil received and paid in the material tank area.

[0095] The oil collection constraint between a material tank area and its tanks refers to the condition that the oil collection volume of a particular material tank area is equal to the sum of the oil collection volumes of all material tanks within that area. The specific expression is as follows:

[0096] IQ t,m,u =∑ j∈u IQ t,m,j (10)

[0097] Formula (10) indicates that the amount of oil collected in the material tank area during period t is equal to the sum of the amounts of oil collected in all material tanks in that material tank area.

[0098] The constraint between a material tank area and its tank tanks on oil discharge means that the amount of oil discharged from a particular material tank area is equal to the sum of the amounts of oil discharged from all the tank tanks within that area. The specific expression is as follows:

[0099] OQ t,m,u =∑ j∈u OQ t,m,j (11)

[0100] Formula (11) indicates that the amount of oil dispensed from the material tank area in period t is equal to the sum of the amounts of oil dispensed from all material tanks in that material tank area.

[0101] The constraint between a material tank area and its inventory refers to the situation where the inventory of a particular material tank area equals the sum of the inventories of all the material tanks within that area. The specific expression is as follows:

[0102] CINV t,m,u =∑ j∈u CINV t,m,j (12)

[0103] Formula (12) indicates that the ending inventory of the material tank area in period t is equal to the sum of the inventory of all material tanks in that material tank area.

[0104] Material tank inventory constraints refer to the requirement that the inventory level of a particular material tank is between its maximum and minimum inventory levels. The specific expression is as follows:

[0105] CL min,j ≤CINV t,m,j (13)

[0106] CINV t,m,j ≤CL max,j (14)

[0107] Formula (14) indicates that the inventory of the material tank in period t is less than the maximum inventory of the material tank, and formula (13) indicates that the inventory of the material tank in period t is greater than the minimum inventory of the material tank.

[0108] The inventory balance constraint for a material container refers to the requirement that the inventory level of a particular material container falls between its maximum and minimum inventory levels. The specific expression is as follows:

[0109] CINV t,m,j = CINV t-1,m,j + IQ t,m,j - OQ t,m,j (15)

[0110] Formula (15) indicates that the ending inventory of the material tank in period t is equal to the beginning inventory plus the difference between the amount of material entering and leaving the material tank.

[0111] Specifically, the meaning and specific expression of each constraint condition in the other constraints are as follows:

[0112] Raw material purchase constraints refer to the amount of raw materials entering the unit and material storage area that falls between the minimum and maximum planned amount of raw materials to be purchased from the plant. The specific expression is as follows:

[0113] PURC min,m,t ≤ ∑ l∈L ∑ s∈S F l,s,m,t + ∑ u∈U IQ t,m,u (16)

[0114] ∑ l∈L ∑ s∈S F l,s,m,t + ∑ u∈U IQ t,m,u ≤ PURC max ,m,t (17)

[0115] Formula (16) indicates that the sum of the amount of material input in the t-cycle unit processing scheme and the amount of oil collected in the material tank area is greater than or equal to the minimum amount of raw material purchased. Formula (17) indicates that the sum of the amount of material input in the t-cycle unit processing scheme and the amount of oil collected in the material tank area is less than or equal to the maximum amount of raw material purchased.

[0116] Product sales volume refers to the quantity of product produced by the unit and material tank area between the minimum and maximum planned sales volume of the product. The specific expression is as follows:

[0117] SELL min,m,t ≤ ∑ l∈L ∑ s∈S D l,s,m,t + ∑ u∈U OQt,m,u (18)

[0118] ∑ l∈L ∑ s∈S D l,s,m,t + ∑ u∈U OQ t,m,u ≤ SELL max ,m,t (19)

[0119] Formula (18) indicates that the product output of the t-cycle processing scheme and the material tank area is greater than or equal to the minimum sales volume of the product, and formula (19) indicates that the product output of the t-cycle processing scheme and the material tank area is greater than or equal to the maximum purchase volume of the product.

[0120] The parameter set in formulas (1) to (19) above is defined as follows:

[0121] l represents the name of the production unit, l∈L;

[0122] s represents the processing scheme of the device, s∈S;

[0123] u represents the name of the material tank area, u∈U;

[0124] j represents the name of the material tank, j∈J;

[0125] t represents the production cycle, t∈T;

[0126] m represents the material name, m∈M;

[0127] The variables in formulas (1) to (19) above are defined as follows:

[0128] This represents the unit processing cost of production unit l;

[0129] F l,s,m,t This represents the amount of all input materials m in the processing scheme s of the production unit l in cycle t;

[0130] C l,s,s, This represents the cost of switching production unit l from processing scheme s to processing scheme s'.

[0131] X l,s,s,,t Indicates whether production device l is switched from processing scheme s to s', a 0-1 variable;

[0132] C j This represents the inventory cost of material container j;

[0133] B l,s,min This represents the minimum processing capacity of processing scheme s in production unit l;

[0134] B l,s,maxThis represents the maximum processing capacity of processing scheme s in production unit l;

[0135] D l,s,n,t This represents the output quantity of the production unit's processing scheme in cycle t;

[0136] Y l,s,m,t This represents the product yield of the production unit's processing scheme in cycle t;

[0137] P u,s,m,t This indicates the proportion of materials input into the processing plan of the production unit during cycle t;

[0138] IQ t,m,u This represents the amount of oil collected in the material tank area during period t.

[0139] OQ t,m,u This represents the amount of oil dispensed from the material tank area during period t.

[0140] CINV t,m,u This represents the inventory level of materials in the tank area during period t.

[0141] OQ t,m,j This indicates the amount of oil dispensed from the material tank during cycle t.

[0142] IQ t,m,j This represents the amount of oil collected in the material tank during cycle t.

[0143] CINV t,m,j This indicates the inventory level of materials in the tank during period t.

[0144] CL min,j This represents the minimum inventory level of the material tank in period t;

[0145] CL max,j This represents the maximum inventory level of the material tank in period t;

[0146] PURC min,m,t This represents the minimum amount of raw materials purchased in cycle t;

[0147] PURC max,m,t This represents the maximum amount of raw materials purchased externally during cycle t;

[0148] SELL min,m,t This represents the minimum sales volume of a product in period t;

[0149] SELL max,m,t This represents the maximum sales volume of the product during period t.

[0150] Optionally, in step S101 above, constructing a refinery production scheduling optimization model based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model includes:

[0151] Add the refinery's production scheduling expert rules to the pre-established production scheduling expert rule library. The production scheduling expert rule library includes at least one of the following: the rule of minimizing unit load fluctuation, the rule of unique unit start-up processing scheme, the rule of asynchronous oil receiving and discharging in material tanks at the same time, the rule of minimizing the number of times material tanks switch continuously receiving oil in the material tank area, and the rule of minimizing the number of times material tanks switch continuously discharging oil in the material tank area.

[0152] The optimization objectives and production constraints in the pre-established refinery production scheduling mathematical model are adjusted based on the production scheduling expert rule base, and a refinery production scheduling optimization model is constructed based on the adjusted optimization objectives and constraints.

[0153] Production scheduling expert rules are formulated from the perspective of production scheduling experts and based on the actual production process of refineries. They provide more scientific and reasonable guidance for the production scheduling of refineries, thus enabling the reasonable optimization of the production process to improve the executability of the scheduling results, efficiently guiding the actual production of refineries, and meeting the needs of actual industrial production applications.

[0154] Optionally, the optimization objectives and constraints in the pre-established refinery production scheduling mathematical model can be adjusted based on the production scheduling expert rule base, including:

[0155] Based on at least one of the following rules from the production scheduling expert rule base: minimum unit load fluctuation rule, minimum number of switching times for continuous oil receiving material tanks in the material tank area, and minimum number of switching times for continuous oil dispensing material tanks in the material tank area, adjust the optimization objective in the refinery production scheduling mathematical model.

[0156] Adjust the production constraints in the refinery's production scheduling mathematical model based on at least one of the unique rules for device start-up processing schemes and asynchronous rules for oil receipt and payment from material tanks at the same time, from the production scheduling expert rule base.

[0157] Optionally, adjust the optimization objective in the refinery production scheduling mathematical model, including:

[0158] To minimize unit load fluctuations, the cost of unit load fluctuations is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0159] To minimize the number of switching times between continuous oil receiving tanks in the material tank area, the cost of switching times between continuous oil receiving tanks in the material tank area is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0160] To minimize the number of switching times between continuous oil delivery tanks in the tank farm, the cost of switching times between continuous oil delivery tanks in the tank farm is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model.

[0161] Adjust the production constraints in the refinery production scheduling mathematical model, including:

[0162] To address the unique rule for processing schemes at the start of a unit, a constraint condition of mutual exclusion of processing schemes is added to the unit constraints included in the production constraints of the refinery production scheduling mathematical model.

[0163] To address the asynchronous oil receiving and disbursement rules for material tanks at the same time, a mutual exclusion constraint condition for oil receiving and disbursement from material tanks is added to the tank area constraints included in the production constraints of the refinery production scheduling mathematical model.

[0164] Specifically, the meaning and expression of each rule in the production scheduling expert rules are as follows:

[0165] To minimize plant load fluctuations, a formula for calculating plant load fluctuations needs to be designed. The specific formula for calculating plant load fluctuations is as follows:

[0166] LORDF=∑ l∈L ∑ s∈S (|∑ m∈M F l,s,m,t -∑ m∈M F l,s,m,t-1 |)(gz-1)

[0167] Formula (gz-1) represents the sum of the absolute values ​​of the load fluctuations of the device during period t, ∑ m∈M F l,s,m,t ∑ represents the end-of-period load of period t. m∈M F l,s,m,t-1 This represents the initial load of period t or the final load of period t-1.

[0168] The optimization objective of the refinery production scheduling mathematical model includes adding unit load fluctuation costs to the production costs. These costs are calculated by multiplying the cumulative value of unit load changes by the penalty cost per unit unit load change. The optimization objective function expression for this added unit load fluctuation cost is as follows:

[0169]

[0170] in, This indicates the cost of equipment load fluctuations.

[0171] To minimize the number of switching operations between material tanks for continuous oil collection in the tank farm, a formula for calculating the number of switching operations between material tanks needs to be designed. The specific expression for the formula is as follows:

[0172]

[0173] Formula (gz-2) represents the number of times the material tanks switch to receive oil within the material tank area during cycle t;

[0174] The optimization objective of the refinery production scheduling mathematical model includes adding the cost of switching between continuous oil receiving tanks in the tank farm to the production cost. This cost is the cumulative number of continuous oil receiving tank switching times multiplied by the unit oil receiving switching penalty cost. The optimization objective function that adds the cost of switching between continuous oil receiving tanks in the tank farm is expressed as follows:

[0175]

[0176] in, This represents the switching cost of continuous oil receiving tanks in the material tank area.

[0177] To minimize the number of material tank switching operations during continuous oil dispensing in the tank farm, a formula for calculating the number of material tank switching operations needs to be designed. The formula for calculating the number of material tank switching operations is as follows:

[0178]

[0179] Formula (gz-3) represents the number of times material tanks switch to oil supply within the material tank area during cycle t;

[0180] The optimization objective of the refinery production scheduling mathematical model includes adding the cost of continuous oil delivery tank switching times to the production cost. This cost item is the cumulative number of continuous oil delivery tank switching times multiplied by the unit oil delivery switching penalty cost. The optimization objective function that adds the cost of continuous oil delivery tank switching times to the production cost is expressed as follows:

[0181]

[0182] in, This represents the switching cost of continuously feeding material tanks in the material tank area.

[0183] To ensure that the processing scheme for the device is enabled is unique, a variable indicating whether the processing scheme is enabled needs to be designed. The specific expression is as follows:

[0184] I t,l,s ∈{0,1}(gz-4)

[0185] Formula (gz-4) represents whether the processing scheme of the t-cycle device is enabled or disabled, with 0 indicating that it is not enabled and 1 indicating that it is enabled.

[0186] In the production constraints of the refinery production scheduling mathematical model, a mutual exclusion constraint for processing schemes is added to the unit constraints. This constraint stipulates that at a certain time, only one of the multiple processing schemes for a certain unit has a valid constraint, while all other constraints related to the remaining processing schemes are invalid. The mathematical expression for the mutual exclusion constraint is:

[0187] ∑ s∈S I t,l,s ≤ 1 (20)

[0188] Formula (20) indicates that the device can only activate one processing scheme within a certain cycle.

[0189] For the asynchronous oil receiving and issuing rule of the material tank at the same time, it is necessary to design variables for whether the material tank receives oil and whether it issues oil. The specific expressions are as follows:

[0190] I t,u,j,iq ∈{0,1} (gz-5)

[0191] I t,u,j,oq ∈{0,1} (gz-6)

[0192] Formula (gz-5) represents the variable of whether the material tank receives oil in cycle t, where 0 indicates no oil is received and 1 indicates oil is received. Formula (gz-6) represents the variable of whether the material tank dispenses oil in cycle t, where 0 indicates no oil is dispensed and 1 indicates oil is dispensed.

[0193] In the production constraints of the refinery production scheduling mathematical model, a mutual exclusion constraint for receiving and discharging oil from material tanks is added to the tank area constraints. This constraint stipulates that at a certain time, a certain material tank can only be in one of the following states: receiving oil, discharging oil, or remaining stationary. The mathematical expression for the mutual exclusion constraint for receiving and discharging oil from material tanks is as follows:

[0194] (I t,u,j,iq + I t,u,j,oq )≤ 1 (21)

[0195] Formula (21) indicates that the same material tank cannot perform oil receiving and oil dispensing operations simultaneously within a certain period.

[0196] The variables in the above formulas (1-1), (1-2), (1-3), (20), and (21) are defined as follows:

[0197] This indicates the unit cost of fluctuation in equipment load; This indicates the switching cost of the oil collection unit; This indicates the cost of switching between fuel delivery units;

[0198] I t,l,s This indicates whether a certain processing scheme is activated by the t-cycle device; 0 indicates deactivated and 1 indicates activated.

[0199] I t,u,j,iq This variable indicates whether the material tank receives oil during period t, with 0 indicating no oil receipt and 1 indicating oil receipt.

[0200] I t,u,j,oq This variable indicates whether the material tank is filled with oil during period t, with 0 indicating no oil filling and 1 indicating oil filling.

[0201] Optionally, a refinery production scheduling optimization model is constructed based on the adjusted optimization objective and constraints, including:

[0202] Based on the adjusted optimization objective, a new optimization objective function is determined; the new objective function is expressed by the following expression: Minimum cost = Minimum processing cost of equipment + Minimum switching cost of equipment processing scheme + Minimum storage cost of material tank + Minimum cost of equipment load fluctuation + Cost of switching times of material tank tank for continuous oil receiving in material tank area + Cost of switching times of material tank tank tank for continuous oil discharging in material tank area.

[0203] Determine new production constraints based on the adjusted production constraints;

[0204] A refinery production scheduling optimization model is constructed based on the optimization scope, the new optimization objective function, and the new production constraints.

[0205] Specifically, a new objective function is determined based on the adjusted optimization objective. The new objective function is expressed by the following expression:

[0206]

[0207] The first item represents the processing cost of the equipment, the second item represents the switching cost of the equipment processing scheme, the third item represents the storage cost of the material tank, the fourth item represents the load fluctuation cost of the equipment, the fifth item represents the number of times the material tanks in the continuous oil receiving area are switched, and the sixth item represents the cost of the number of times the material tanks in the continuous oil discharging area are switched.

[0208] New constraints are determined based on the adjusted production constraints. These new constraints include production constraints in the refinery production scheduling mathematical model, as well as production constraints added based on the unique rules for unit start-up processing schemes and the asynchronous rules for oil receipt and payment from material tanks at the same time in the production scheduling expert rule base.

[0209] Optionally, in step S102 above, the actual production parameters of the refinery are input into the refinery production scheduling optimization model and solved to obtain the model solution results, including:

[0210] Input the actual production parameters of the refinery into the optimization model, set the solution time and GAP parameters of the optimization model, and use a solver to solve the optimization model to obtain the parameter solution results of the optimization model. The actual production parameters include at least one of the following: optimization cycle, product yield of the unit processing scheme, material tank inventory, raw material purchase plan, product sales plan, and production cost.

[0211] Specifically, the solution time and GAP parameter value of the model can be set according to actual production needs. For example, the solution time of the optimized model can be set to no more than 30 seconds and the GAP value to be 0.01%. The GUROBI solver is used to optimize the solution of the established mathematical model. The solution time of the model is set so that the model can obtain the optimal solution in a limited time, thereby obtaining the solution result of the model accurately and quickly.

[0212] Specifically, the actual production parameters of a refinery can be obtained during the production process. Different production processes and production plans can yield different actual production parameters. Below is an example of actual production parameters.

[0213] The optimization cycle refers to the range of production scheduling optimization cycles, as shown in Table 1:

[0214] Table 1

[0215] Project Name numerical values Start time 2024 / 2 / 22 06:00:00 End time 2024 / 2 / 29 06:00:00 Time scale (hours) 24

[0216] In Table 1, the time scale is 24 hours, indicating that the interval of one cycle is 24 hours.

[0217] Unit yield refers to the yield information of the output materials or products of the unit processing scheme. Unit yield corresponds to "Y" in formula (6). l,s,n,t As shown in Table 2:

[0218] Table 2

[0219]

[0220] In Table 2, a yield of 0 indicates that no material or product was produced, and the loss in the material name indicates that there was a loss during the production process.

[0221] Material tank inventory refers to the beginning inventory information of material tanks. The beginning inventory of material tanks is the CINV at t=1. t-1,m,j As shown in Table 3:

[0222] Table 3

[0223] Tank farm coding Tank Farm Name Material tank name Beginning inventory (tons) F8G Alkylated oil 5241TK6103 3192.16 F8G Alkylated oil 5241TK6104 909.43 ... ... ... ... EYG propylene 5233TK5301 682.359 EYG propylene 5233TK5302 136.871 EYG propylene 5233TK5303 115.503 EYG propylene 5233TK5304 440.521

[0224] The feedstock delivery plan refers to the feedstock delivery information, as shown in Table 4. The minimum feedstock delivery plan in Table 4 corresponds to PURC in formula (16). min,m,t The maximum planned intake of crude oil corresponds to PURC in formula (17). max,m,t .

[0225] Table 4

[0226]

[0227] Product delivery plan refers to product delivery information, as shown in Table 5. The minimum product delivery plan in Table 5 corresponds to SELL in formula (18). min,m,t The maximum planned output of the product corresponds to SELL in formula (19). max,m,t .

[0228] Table 5

[0229]

[0230] Production cost refers to the unit cost information for production, as shown in Table 6:

[0231] Table 6

[0232] Project Name numerical values Unit processing cost of the equipment (RMB / ton) 10 Unit cost of switching processing schemes (RMB / time) 1000 Material inventory unit cost (RMB / ton / hour) 20 Unit cost per ton-hour due to load fluctuations 0.5 Material tank oil recovery switching cost (RMB / time) 100 Material tank oil switching cost (RMB / time) 100

[0233] By inputting the actual production parameters mentioned above into the refinery production scheduling optimization model, assigning values ​​to the corresponding variables, and solving the model, the solution results of the optimization model can be obtained.

[0234] In step S103 above, the refinery production scheduling business results are obtained based on the model solution results, including:

[0235] The model solution results are instantiated to obtain the refinery production scheduling business results. The production scheduling business results include at least one of the following: unit input and output information, unit load information, material tank area oil receipt and payment information, material tank inventory information, raw material purchase quantity arrangement information, and product sales arrangement information.

[0236] Based on the solution results of step S102, the mathematical solution of the model can be obtained. These mathematical solutions are instantiated and output, and transformed into the business scheduling results of the refinery. This enables scientific optimization of the production process and reasonable arrangement of production scheduling based on the business scheduling results.

[0237] Specifically, the mathematical solution of the optimization model is instantiated and output, and transformed into the business scheduling results of the refinery. The business scheduling results include at least one of the following: unit input and output information, unit load information, oil receipt and payment information of material tank area, material tank inventory information, raw material purchase quantity arrangement information, and product sales arrangement information.

[0238] Specifically, the detailed arrangement information of the service scheduling results is as follows:

[0239] The input-output ratio of the equipment refers to the detailed production and processing arrangements of the equipment within the optimization cycle, as shown in Table 7:

[0240] Table 7

[0241]

[0242]

[0243] Taking the second row of Table 7 as an example, this table can be interpreted as follows: during the optimization period, 0 tons of cracked hydrogen were fed into the full-density polyethylene unit FDP11 in the DFDA-7050 processing scheme. The loss in the table can be regarded as a special material, or it can be understood as lost and nowhere to go.

[0244] The unit load refers to the detailed load arrangement information of the unit within the optimization period, as shown in Table 8:

[0245] Table 8

[0246]

[0247] Taking the second row of Table 8 as an example, this table can be interpreted as follows: during the optimization period, the hourly load of the full-density polyethylene unit I FDP1 is 85.83 tons. The unit load can also be understood as the total amount of material that the unit can input.

[0248] The oil receipt and payment information for the material tank area refers to the detailed arrangement of oil receipt and payment for the material tanks within the optimization cycle, as shown in Table 9.

[0249] Table 9

[0250]

[0251]

[0252] Taking the second and third rows of Table 9 as an example, the table can be interpreted as follows: during the optimization cycle, the alkylation unit needs to supply 1552.5 kg of alkylation oil to the F8G tank; the F8G material tank provides 1633.26483 kg of alkylation oil to the gasoline blending pool I.

[0253] Material tank inventory refers to the detailed inventory arrangement information of material tanks within the optimization cycle, as shown in Table 10:

[0254] Table 10

[0255]

[0256] Taking the second row of Table 10 as an example, this can be interpreted as follows: During the optimization period, 35.33 tons of oil were added to material tank 5211TK3101 in the residual oil tank area. If this material tank was added to or removed from the tank, and the amount added and the amount removed were inconsistent, then the inventory of the material tank changed, that is, the ending inventory was inconsistent with the beginning inventory.

[0257] The feedstock delivery arrangement refers to the detailed arrangement information of feedstock delivery within the optimization cycle, as shown in Table 11.

[0258] Table 11

[0259]

[0260] Taking the second row of Table 11 as an example, the table can be interpreted as follows: 161 tons of isopentane were purchased during the optimization period.

[0261] Product production arrangement refers to the detailed arrangement information of product delivery within the optimization cycle, as shown in Table 12.

[0262] Table 12

[0263]

[0264] Taking the second row of Table 12 as an example, this table can be interpreted as follows: during the optimization period, 8239.68 tons of raw material DFDC-7050 were sold.

[0265] After verification in actual production, the production scheduling of the refinery based on the above business scheduling results is highly accurate and more reasonable and scientific. The business scheduling results can be implemented in the actual production process, and the executability is high. This avoids the problem that the optimization results obtained by existing operations research techniques are not executable in the actual production process, and improves the production efficiency of the refinery.

[0266] Based on the same inventive concept, embodiments of the present invention also provide a refinery production scheduling optimization device, which can be installed in equipment with computing power, and the structure of the device is as follows. Figure 2 As shown, it includes:

[0267] The optimization model building module 11 is used to build a refinery production scheduling optimization model based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the actual production process of the refinery.

[0268] The optimization model solving module 12 is used to input the actual production parameters of the refinery into the refinery production scheduling optimization model and solve it to obtain the model solution results;

[0269] The business result generation module 13 is used to obtain the refinery production scheduling business results based on the model solution results.

[0270] Regarding the refinery production scheduling optimization device in the above embodiments, the specific methods by which each module performs its operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0271] This invention also provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement a refinery production scheduling optimization method.

[0272] This invention also provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a refinery production scheduling optimization method.

[0273] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0274] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0275] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0276] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0277] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0278] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0279] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A refinery production scheduling optimization method, characterized in that, include: A refinery production scheduling optimization model is constructed based on refinery production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the actual production process of the refinery. The actual production parameters of the refinery are input into the refinery production scheduling optimization model and solved to obtain the model solution results; The refinery production scheduling results are obtained based on the solution results of the model.

2. The method as described in claim 1, characterized in that, The pre-established mathematical model for refinery production scheduling includes: Starting from the refinery's production process, production optimization objectives and optimization scope are determined based on the refinery's production scheduling objects and production business requirements. Based on the optimization objectives, an optimization objective function is determined. The optimization scope refers to the production processes in the refinery that need to be optimized. A mathematical model for refinery production scheduling is established based on the optimization scope, refinery production constraints, and the optimization objective function.

3. The method as described in claim 2, characterized in that, The optimization objectives include: minimizing production costs; The production cost includes at least one of the following: equipment processing cost, equipment processing scheme switching cost, and material tank storage cost; The optimization objective function is expressed as: Minimum cost = Minimum equipment processing cost + Minimum equipment processing scheme switching cost + Minimum material tank storage cost; The production constraints include equipment constraints, tank farm constraints, and other constraints. The device constraints include at least one of the following: device processing scheme load constraints, device processing scheme input raw material ratio normalization constraints, device processing scheme output product yield normalization constraints, and device processing scheme input-output material balance constraints. The tank farm constraints include at least one of the following: material tank farm inventory balance constraint, material tank farm and material tank receiving constraint, material tank farm and material tank dispensing constraint, material tank farm and material tank inventory constraint, material tank inventory quantity constraint, and material tank inventory balance constraint. The other constraints include at least one of the following: constraints on the amount of raw materials purchased and constraints on the amount of products sold.

4. The method as described in claim 2, characterized in that, A refinery production scheduling optimization model is constructed based on refinery production scheduling expert rules and a pre-established refinery production scheduling mathematical model, including: Add the refinery's production scheduling expert rules to a pre-established production scheduling expert rule library. The production scheduling expert rule library includes at least one of the following: minimum unit load fluctuation rule, unique unit start-up processing scheme rule, asynchronous oil receiving and discharging rule for material tanks at the same time rule, minimum number of switching times for continuous oil receiving material tanks in the material tank area rule, and minimum number of switching times for continuous oil discharging material tanks in the material tank area rule. The optimization objectives and production constraints in the pre-established refinery production scheduling mathematical model are adjusted based on the production scheduling expert rule base, and a refinery production scheduling optimization model is constructed based on the adjusted optimization objectives and constraints.

5. The method as described in claim 4, characterized in that, The adjustment of the optimization objective and constraints in the pre-established refinery production scheduling mathematical model based on the production scheduling expert rule base includes: Based on at least one of the following rules from the production scheduling expert rule base: minimum unit load fluctuation rule, minimum number of switching times for continuous oil receiving material tanks in the material tank area, and minimum number of switching times for continuous oil dispensing material tanks in the material tank area, adjust the optimization objective in the refinery production scheduling mathematical model. Adjust the production constraints in the refinery's production scheduling mathematical model based on at least one of the unique rules for device start-up processing schemes and asynchronous rules for oil receipt and payment from material tanks at the same time, from the production scheduling expert rule base.

6. The method as described in claim 5, characterized in that, The optimization objectives in the adjusted refinery production scheduling mathematical model include: To minimize unit load fluctuations, the unit load fluctuation cost is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model. To minimize the number of switching times between continuous oil receiving tanks in the material tank area, the cost of switching times between continuous oil receiving tanks in the material tank area is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model. To minimize the number of times material tanks need to be switched during continuous oil delivery in the material tank area, the cost of the number of times material tanks need to be switched during continuous oil delivery is added to the production cost included in the optimization objective of the refinery production scheduling mathematical model. The adjustment of production constraints in the refinery production scheduling mathematical model includes: To address the unique rule for the processing scheme of the unit, a constraint condition of mutual exclusion of processing schemes is added to the unit constraints included in the production constraints of the refinery production scheduling mathematical model. To address the asynchronous oil receiving and disbursement rule for material tanks at the same time, a mutual exclusion constraint condition for oil receiving and disbursement from material tanks is added to the tank area constraint condition included in the production constraint condition of the refinery production scheduling mathematical model.

7. The method as described in claim 4, characterized in that, Based on the adjusted optimization objective and constraints, a refinery production scheduling optimization model is constructed, including: A new optimization objective function is determined based on the adjusted optimization objective; the new objective function is expressed by the following expression: Minimum cost = Minimum processing cost of equipment + Minimum switching cost of equipment processing scheme + Minimum storage cost of material tank + Minimum cost of equipment load fluctuation + Cost of switching times of material tank tank for continuous oil receiving in material tank area + Cost of switching times of material tank tank tank for continuous oil discharging in material tank area. Determine new production constraints based on the adjusted production constraints; A refinery production scheduling optimization model is constructed based on the optimization range, the new optimization objective function, and the new production constraints.

8. The method as described in claim 1, characterized in that, The process of inputting the actual production parameters of the refinery into the refinery production scheduling optimization model and solving it to obtain the model solution results includes: The actual production parameters of the refinery are input into the optimization model. The solution time and GAP parameters of the optimization model are set, and the optimization model is solved by the solver to obtain the parameter solution results of the optimization model. The actual production parameters include at least one of the following: optimization cycle, product yield of the unit processing scheme, material tank inventory, raw material purchase plan, product sales plan, and production cost.

9. The method as described in claim 1, characterized in that, The refinery production scheduling business results obtained based on the model solution results include: The solution results of the model are instantiated to obtain the refinery production scheduling business results. The production scheduling business results include at least one of the following: unit input and output information, unit load information, material tank area oil receipt and payment information, material tank inventory information, raw material purchase quantity arrangement information, and product sales arrangement information.

10. A refinery production scheduling optimization device, characterized in that, include: The optimization model building module is used to construct a refinery production scheduling optimization model based on the refinery's production scheduling expert rules and a pre-established refinery production scheduling mathematical model. The production scheduling expert rules are formulated according to the refinery's actual production process. The optimization model solving module is used to input the actual production parameters of the refinery into the refinery production scheduling optimization model and solve it to obtain the model solution results; The business result generation module is used to obtain the refinery production scheduling business results based on the solution results of the model.

11. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed by a processor, implement the refinery production scheduling optimization method according to any one of claims 1-9.

12. A computer device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the refinery production scheduling optimization method according to any one of claims 1-9.

Images