Crude oil scheduling optimization method, equipment, medium and product

Abstract

The invention relates to the technical field of industrial control, in particular to a crude oil scheduling optimization method and device, a medium and a product. According to the method, through a preset long-term scheduling optimization model, long-term scheduling production scheduling data corresponding to a crude oil production process are obtained, and through the long-term scheduling production scheduling data, the long-term scheduling optimization model is solved to generate a long-term scheduling scheme. And then, according to a preset short-term scheduling optimization model, obtaining short-term scheduling production scheduling data corresponding to the crude oil production process, thereby solving the short-term scheduling optimization model according to a preset hybrid optimization algorithm in combination with the short-term scheduling production scheduling data and the long-term scheduling scheme, and generating a short-term scheduling scheme. Resource planning and operation scheduling are carried out on crude oil production, and the crude oil production efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial control, and in particular to a crude oil scheduling optimization method, device, medium and product. BACKGROUND

[0002] In the production management of a refining enterprise, crude oil scheduling is a core link at the front end of the production chain, and needs to take into account resource planning for long-term scheduling (for example, every ten days or every month) and operation execution for short-term scheduling (for example, every hour or every day), so as to realize accurate organization and efficient operation of the production process.

[0003] A traditional crude oil scheduling method relies on manual experience and electronic table simulation, which is not only time-consuming and inefficient, but also lacks systematicness, and it is difficult to generate a global optimization scheme that meets resource constraints and operation feasibility at the same time, greatly reducing the efficiency of crude oil scheduling. Moreover, the traditional crude oil scheduling method usually uses mathematical optimization, which is difficult to handle large-scale discrete decision variables (for example, crude oil tank and device matching relationship) and non-convex non-linear process constraints (for example, mixed oil property coupling, yield balance), resulting in that the traditional scheduling is difficult to efficiently solve complex scheduling scenarios.

[0004] Therefore, there is an urgent need for a crude oil scheduling optimization method to improve the efficiency of crude oil scheduling. SUMMARY

[0005] The present application provides a crude oil scheduling optimization method, device, storage medium and program product to improve the efficiency of crude oil scheduling.

[0006] In a first aspect, the present application provides a crude oil scheduling optimization method, which comprises:

[0007] Based on a preset long-term scheduling optimization model, long-term scheduling scheduling data corresponding to a crude oil production process is obtained; the long-term scheduling optimization model is used to plan resources for crude oil in a first time scale, and the long-term scheduling scheduling data represents resource planning data and operation scheduling data of the crude oil production process in the first time scale;

[0008] Based on the long-term scheduling scheduling data, the long-term scheduling optimization model is solved to generate a long-term scheduling scheme; the long-term scheduling scheme represents a crude oil scheduling scheme with the minimum number of refining scheme switching times in the first time scale;

[0009] Based on a preset short-term scheduling optimization model, short-term scheduling scheduling data corresponding to a crude oil production process is obtained; the short-term scheduling optimization model is used to schedule operations for crude oil in a second time scale, the first time scale is greater than the second time scale, and the short-term scheduling scheduling data represents resource planning data and operation scheduling data of the crude oil in the second time scale;

[0010] solving the short-term scheduling optimization model based on a preset hybrid optimization algorithm, in combination with the short-term scheduling production data and the long-term scheduling scheme, to generate a short-term scheduling scheme; the short-term scheduling scheme represents a crude oil scheduling scheme with a minimum number of feed switching times of the crude oil tank in the second time scale.

[0011] Optionally, the long-term scheduling optimization model is constructed based on the following steps:

[0012] obtaining resource constraints and a first optimization objective function of the long-term scheduling optimization model; the long-term constraints include at least one of material balance constraints, upper and lower inventory constraints of the oil tank, feed constraints of the crude oil distillation unit, output constraints of the crude oil distillation unit, wax residue oil yield constraints, and scheme switching constraints, and the first optimization objective function is used to minimize the total number of times of switching of the refining scheme;

[0013] constructing the long-term scheduling optimization model based on the resource constraints and the first optimization objective function.

[0014] Optionally, the short-term scheduling optimization model is constructed based on the following steps:

[0015] obtaining operation constraints and a second optimization objective function of the short-term scheduling optimization model; the operation constraints include at least one of unloading operation constraints between the oil tanker and the crude oil tank, crude oil tank selection constraints, and feed relationship constraints between the crude oil tank and the crude oil distillation unit, and the second optimization objective function is used to minimize the number of feed switching times of the crude oil tank;

[0016] constructing the short-term scheduling optimization model based on the operation constraints and the second optimization objective function.

[0017] Optionally, solving the long-term scheduling optimization model based on the long-term scheduling production data to generate a long-term scheduling scheme includes:

[0018] determining a mathematical representation corresponding to the long-term scheduling optimization model based on the long-term scheduling production data;

[0019] obtaining the long-term scheduling scheme by solving the mathematical representation for an optimal solution based on a preset solver.

[0020] Optionally, solving the short-term scheduling optimization model based on a preset hybrid optimization algorithm, in combination with the short-term scheduling production data and the long-term scheduling scheme, to generate a short-term scheduling scheme includes:

[0021] performing population initialization based on the short-term scheduling production data to generate individual codes, the individual codes representing tank selection and oil allocation of each sub-period;

[0022] The particle swarm optimization algorithm is used to iteratively optimize the oil tank selection, and a mathematical programming method is used to determine the oil loading of each oil tank to generate the short-term scheduling scheme.

[0023] Optionally, the particle swarm optimization algorithm is used to iteratively optimize the oil tank selection, including:

[0024] When the optimization result output by the iterative optimization is an infeasible solution, a preset genetic algorithm is used to correct the feed formula to obtain a corrected short-term scheduling scheme.

[0025] Optionally, the long-term scheduling production data and the short-term scheduling production data correspond to scheduling production data sets in the first time scale and the second time scale, respectively; the scheduling production data set includes scheduling time period, ship arrival plan, tank farm information, crude oil information and crude oil vacuum distillation unit processing information; the ship arrival plan includes oil tanker arrival time, oil carrying capacity and oil unloading rate; the tank farm information includes the number of oil tanks, initial inventory and inventory upper and lower limits of the crude oil tank farm, the wax oil tank farm and the residual oil tank farm; the crude oil information includes crude oil attribute value, yield and produced wax and residual oil types; and the crude oil vacuum distillation unit processing information includes feed upper and lower limits and attribute upper and lower limits.

[0026] In a second aspect, the present application provides a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements any one of the crude oil scheduling optimization methods in the first aspect when executing the computer program.

[0027] In a third aspect, the present application provides a computer storage medium, and the computer readable storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement any one of the crude oil scheduling optimization methods in the first aspect.

[0028] In a fourth aspect, the present application provides a computer program product, including computer program instructions, and the computer program instructions are executed by a processor to implement any one of the crude oil scheduling optimization methods in the first aspect.

[0029] The present application has the following advantages:

[0030] This application provides a crude oil scheduling optimization method, equipment, medium, and product. The method obtains long-term scheduling data corresponding to the crude oil production process using a preset long-term scheduling optimization model, and solves the long-term scheduling optimization model using this data to generate a long-term scheduling scheme. Next, based on a preset short-term scheduling optimization model, it obtains short-term scheduling data corresponding to the crude oil production process. Then, using a preset hybrid optimization algorithm, it combines the short-term scheduling data and the long-term scheduling scheme to solve the short-term scheduling optimization model, generating a short-term scheduling scheme. This allows for resource planning and operational scheduling of crude oil production, improving crude oil production efficiency. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0032] Figure 1 A flowchart illustrating a crude oil scheduling optimization method provided in this application embodiment;

[0033] Figure 2 A schematic diagram illustrating the processing procedure of a hybrid optimization algorithm provided in an embodiment of this application;

[0034] Figure 3 A schematic diagram of an individual code provided for an embodiment of this application;

[0035] Figure 4 A schematic diagram of a crude oil dispatching process in a refining and chemical enterprise is provided as an embodiment of this application;

[0036] Figure 5 This is a schematic diagram of oil tanker information provided in an embodiment of this application;

[0037] Figure 6 This is a schematic diagram of initial information for a crude oil tank provided in an embodiment of this application;

[0038] Figure 7 This is a schematic diagram of initial information for a wax residue oil tank provided in an embodiment of this application;

[0039] Figure 8 This is a schematic diagram of processing data information for an atmospheric and vacuum distillation device provided in an embodiment of this application;

[0040] Figure 9 This is a schematic diagram of crude oil property information provided in an embodiment of this application;

[0041] Figure 10This is a schematic diagram of crude oil yield information provided in an embodiment of this application;

[0042] Figure 11 A schematic diagram of a long-term scheduling scheme provided in an embodiment of this application;

[0043] Figure 12 A schematic diagram of a short-term scheduling scheme provided in an embodiment of this application;

[0044] Figure 13 A Gantt chart diagram illustrating a short-term scheduling scheme provided in an embodiment of this application;

[0045] Figure 14 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0047] The terms "first" and "second" in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. The term "multiple" in this application can mean at least two, for example, two, three, or more, and this application does not impose limitations.

[0048] The term "and / or" in the embodiments of this application is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0049] It is understood that the following specific embodiments of this application involve data related to the crude oil production process. When the various embodiments of this application are applied to specific products or technologies, relevant licenses or consents are required, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, relevant volunteers can be recruited and agreements can be signed to authorize their data, thereby enabling the implementation using the data of these volunteers; alternatively, implementation can be carried out within an authorized organization, using data from members of the organization to implement the following implementation methods for data management; or, in specific implementations, the relevant data used are all simulated data, such as simulated data generated in a virtual scenario.

[0050] The design concept of the embodiments of this application is briefly introduced below:

[0051] Production planning and scheduling, as the core of production management in refining and chemical enterprises, plays a crucial role in helping enterprises reduce costs, improve quality, and increase efficiency. The production planning system includes long-term scheduling (ten-day / monthly) resource planning and short-term scheduling (hourly / daily) operational execution. Long-term scheduling focuses on material procurement, processing quantities, unit load, and product allocation; short-term scheduling emphasizes material coordination, material transportation planning, process sequencing, and operating condition control, thereby achieving real-time, precise organization and efficient operation of the production process. Crude oil scheduling, as a core upstream link in the refining production chain, consists of three parts: crude oil scheduling, production unit scheduling, and refined product blending scheduling. It must balance long-term scheduling resource planning with short-term scheduling operational execution to improve crude oil scheduling efficiency and achieve precise organization and efficient operation of the production process.

[0052] However, with the ever-expanding production scale of refining and chemical enterprises, the processes have become increasingly complex, resource constraints have continued to increase, and the properties of crude oil varieties have shown significant differences. The complexity of such large-scale production processes and stringent product quality requirements often make it difficult for crude oil scheduling schemes to meet planned needs. Currently, refining and chemical enterprises still rely on manual experience and spreadsheet simulations to develop scheduling schemes, which suffers from drawbacks such as time-consuming inefficiency and insufficient systematicity, making it difficult to generate globally optimized schemes that simultaneously meet resource constraints and operational feasibility. Furthermore, traditional crude oil scheduling optimization methods typically employ mathematical optimization, making it difficult to handle large-scale discrete decision variables (e.g., the matching relationship between crude oil tanks and equipment) and non-convex nonlinear process constraints (e.g., the coupling of mixed oil properties and yield balance), thus failing to effectively support the solution of complex scheduling scenarios.

[0053] In view of the above problems, this application provides a crude oil scheduling optimization method. This method obtains long-term scheduling data corresponding to the crude oil production process using a preset long-term scheduling optimization model, and solves the long-term scheduling optimization model using this data to generate a long-term scheduling scheme. Next, based on a preset short-term scheduling optimization model, it obtains short-term scheduling data corresponding to the crude oil production process. Then, according to a preset hybrid optimization algorithm, it combines the short-term scheduling data and the long-term scheduling scheme to solve the short-term scheduling optimization model, generating a short-term scheduling scheme. This allows for resource planning and operational scheduling of crude oil production, improving crude oil production efficiency.

[0054] Furthermore, this application provides a crude oil scheduling optimization method that addresses actual resource and operational needs. It further decomposes the long-term resource-oriented refining scheduling scheme into a short-term operational-oriented crude oil scheduling scheme, promoting the connection between long-term resource planning and short-term operational scheduling, thereby achieving multi-timescale collaborative scheduling of crude oil. Moreover, this application addresses the shortcomings of existing optimization techniques in handling crude oil scheduling and the connection between resource planning and operational execution by providing a multi-timescale collaborative crude oil scheduling optimization method. This method constructs a multi-timescale collaborative crude oil scheduling optimization model that includes long-term and short-term crude oil scheduling sub-models. For the resource allocation and production scheduling of actual refineries, it adopts a hierarchical optimization structure: the long-term scheduling layer operates on a ten-day / monthly cycle, generating the resource-optimal crude oil processing scheme with the core objective of minimizing the number of refining formula switching under constraints such as tanker arrival plans, unit configuration, and oil transportation; the short-term scheduling layer operates on a daily / hourly cycle, inheriting the long-term scheduling refining formula, focusing on constraints such as unit feed sequence and tank farm logistics balance, and generating a highly operable refined scheduling scheme with the optimization direction of minimizing the number of crude oil tank switching. In this way, dynamic collaboration is achieved between the two levels through a rolling optimization mechanism. The long-term plan provides the total processing volume and formula boundaries for the short-term scheduling, while the short-term scheduling performs refined operational optimization based on the long-term plan. Next, an evolutionary optimization algorithm based on the decomposition of the long-term scheduling plan is used to decompose the ten-day plan into daily plan operations, forming a hierarchical optimization system of "resource planning → operation execution". Thus, this embodiment of the application effectively solves the problem of the disconnect between resource planning and operation execution in the traditional model by organically integrating mathematical programming and evolutionary algorithms. It achieves the integration and connection from global resource optimization at the strategic level to refined operational control at the execution level, providing a systematic solution for large-scale crude oil scheduling problems in refining enterprises.

[0055] Please refer to Figure 1 The following is a flowchart illustrating a crude oil scheduling optimization method provided in an embodiment of this application. The specific implementation process of this method is as follows:

[0056] Step 101: Based on the preset long-term scheduling optimization model, obtain the long-term scheduling data corresponding to the crude oil production process.

[0057] In this embodiment, the long-term scheduling optimization model is a mathematical programming model used for crude oil resource planning on a first time scale (e.g., ten days or a month). It primarily transforms the resource allocation problem in crude oil scheduling into a solvable optimization problem through predefined constraints and objective functions. The long-term scheduling production data represents the resource planning and operational scheduling data of the crude oil production process at the corresponding first time scale, providing a comprehensive and accurate data reference for subsequent resource planning optimization and enabling the accurate generation of long-term scheduling schemes.

[0058] In one possible implementation, the long-term and short-term scheduling data in this embodiment correspond to scheduling datasets at different time scales, such as a first time scale and a second time scale, with the first time scale being larger than the second time scale. The scheduling dataset includes scheduling time cycles, incoming vessel plans, tank farm information, crude oil information, and atmospheric and vacuum distillation unit processing information during the crude oil production process. Furthermore, the scheduling dataset can be obtained through a model input interface and standardized according to the static configuration of the actual production system to ensure data integrity and consistency.

[0059] Specifically, in this embodiment, the ship arrival plan includes the tanker's arrival time, oil load, and unloading rate; the tank farm information includes the number of oil tanks, initial inventory, and upper and lower inventory limits for crude oil tank farms, wax oil tank farms, and residue oil tank farms; the crude oil information includes crude oil attribute values, yield, and the type of wax residue oil produced; and the atmospheric and vacuum distillation unit processing information includes feed upper and lower limits and attribute upper and lower limits.

[0060] In one possible implementation, before performing scheduling optimization processing through the long-term scheduling optimization model and the short-term scheduling optimization model, the embodiments of this application can construct a crude oil scheduling optimization model that meets the needs of long-term resource planning and short-term operation scheduling based on the principle of multi-time scale collaboration, namely, the long-term scheduling optimization model and the short-term scheduling optimization model.

[0061] Specifically, the long-term scheduling optimization model in this application embodiment can be constructed based on the following steps:

[0062] The resource constraints and the first objective function of the long-term scheduling optimization model are obtained, and the long-term scheduling optimization model is constructed based on the resource constraints and the first objective function. The long-term constraints include at least one of the following: material balance constraints, upper and lower limits of oil tank inventory constraints, atmospheric and vacuum distillation unit feed constraints, atmospheric and vacuum distillation unit output constraints, wax residue oil yield constraints, and scheme switching constraints. The first objective function is used to minimize the total number of refining scheme switching operations. Thus, the long-term scheduling optimization model in this application can achieve the optimization objective of minimizing the number of refining scheme switching operations while satisfying constraints such as material balance, crude oil properties, side-stream production, and wax residue inventory limits, improving the operability and efficiency of actual scheduling and better meeting production needs.

[0063] Specifically, the constraints of the long-term scheduling optimization sub-model in this application embodiment may include:

[0064] (1) The material balance constraints for oil tankers, crude oil tanks, wax oil tanks, and residual oil tanks are expressed as follows:

[0065] (1)

[0066] (2)

[0067] (3)

[0068] (4)

[0069] (5)

[0070] (6)

[0071] The above formulas (1)-(6) sequentially determine the oil tanker's oil load, the total inventory of each crude oil tank, and the inventory of wax oil and residual oil tanks after the end of each sub-cycle in the overall scheduling cycle.

[0072] Among them, in formula (1) and Let represent the initial inventory of crude oil j carried by the vth oil tanker and the inventory at the end of the tth sub-cycle, respectively;

[0073] This represents the quantity of type j crude oil transferred by the vth oil tanker to the kth crude oil tank in the tth sub-cycle;

[0074] Formula (2) and Let represent the initial inventory of the k-th crude oil tank and its inventory at the end of the t-th sub-period, respectively. This represents the amount of oil transferred from the k-th crude oil tank to the m-th atmospheric and vacuum distillation unit during the t-th sub-cycle;

[0075] In formula (3) and Let represent the initial inventory of the j-th component oil in the k-th crude oil tank and its inventory at the end of the t-th sub-cycle, respectively. This represents the amount of the j-th component oil transferred from the k-th crude oil tank to the m-th atmospheric and vacuum distillation unit during the t-th sub-cycle;

[0076] Formula (4) requires that the total amount of crude oil transported from the crude oil tank to the atmospheric and vacuum distillation unit be the sum of the quantities of each component oil;

[0077] In formula (5) and Let represent the initial inventory of the wax type 1 can and its inventory at the end of the t-th sub-cycle, respectively. This represents the quantity of wax oil of type wax produced by the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle. This represents the amount of wax oil consumed at the end of the t-th sub-cycle;

[0078] In formula (6) and Let represent the initial inventory of the nth type of residual oil tank and its inventory at the end of the t-th sub-cycle, respectively. This represents the quantity of the nth type of residue oil produced by the mth atmospheric and vacuum distillation unit in the tth sub-cycle. This represents the consumption of the nth type of residual oil in the tth sub-cycle.

[0079] (2) All vessels must unload all the crude oil they are carrying within the entire scheduling cycle:

[0080] (7)

[0081] (3) Upper and lower limits of oil tank inventory constraints:

[0082] (8)

[0083] (9)

[0084] (10)

[0085] Formulas (8)-(10) respectively limit the upper and lower limits of the liquid level of each crude oil tank, the upper and lower limits of the inventory of the wax oil tank and the upper and lower limits of the inventory of the oil tank, so as to ensure that crude oil, wax oil and residual oil are all within the safe inventory range.

[0086] In formula (8) and These represent the upper and lower limits of the crude oil level in the k-th crude oil tank, respectively. This represents the bottom area of ​​the k-th crude oil tank. This represents the density of the j-th type of crude oil;

[0087] In formula (9) and These represent the upper and lower limits of the inventory of the wax type; in formula (10) and These represent the upper and lower limits of the inventory of the nth type of residual oil, respectively.

[0088] (4) Feed constraints for atmospheric and vacuum distillation units, including feed load constraints and constraints on key feed attributes (i.e., sulfur content, acid value, and density), are as follows:

[0089] a. Feed load constraint:

[0090] (11)

[0091] (12)

[0092] (13)

[0093] Formula (11) indicates that the feed rate of the atmospheric and vacuum distillation unit should be consistent with the oil delivery rate of each crude oil. This represents the feed rate of the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle. This represents the amount of crude oil of type j supplied to the atmospheric and vacuum distillation unit in the t-th sub-cycle.

[0094] In formula (12) and The feed rate of the atmospheric and vacuum distillation unit is limited, representing the upper and lower limits of the feed rate of the m-th atmospheric and vacuum distillation unit; Formula (13) indicates that a single atmospheric and vacuum distillation unit can receive a maximum of [feed rate] at any given time. Crude oil transportation.

[0095] b. Constraints on key feed properties (i.e., sulfur content, acid value, and density) for atmospheric and vacuum distillation units:

[0096] (14)

[0097] In this way, the various feed properties of the atmospheric and vacuum distillation unit can be controlled within the allowable range by controlling the oil delivery rate;

[0098] In formula (14) and These represent the upper and lower limits of the l-th feed property in the m-th atmospheric and vacuum distillation unit, respectively.

[0099] (5) Output constraints of atmospheric and vacuum distillation units, including yield constraints of various types of residue oil and yield constraints of various types of wax residue oil, as detailed below:

[0100] a. Yield constraints for various types of residual oil:

[0101] (15)

[0102] (16)

[0103] (17)

[0104] (18)

[0105] Among them, in formula (15) This represents the amount of crude oil transported in the m-th atmospheric and vacuum distillation unit for the production of the n-th type of residue oil; This represents the yield of residue oil produced from crude oil of type j in the m-th atmospheric and vacuum distillation unit; This represents the quantity of the nth residue oil product produced by the mth atmospheric and vacuum distillation unit in the tth sub-cycle; in formula (16) This represents the total amount of residue oil produced by the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle; formula (17) limits the upper and lower limits of residue oil production, where and and represent the upper and lower limits of the output of the nth type of residue oil produced in the m-th atmospheric and vacuum distillation unit, respectively; formula (18) restricts a single atmospheric and vacuum distillation unit to produce only one type of residue oil per day, where It is a binary variable of 0 and 1. If the m-th atmospheric and vacuum distillation unit produces n residue oil in the t-th sub-cycle, then this term is 1, otherwise it is 0.

[0106] b. Yield constraints for various types of wax residue oil:

[0107] (19)

[0108] (20)

[0109] (twenty one)

[0110] Among them, in formula (19) This represents the amount of crude oil of type j supplied to the atmospheric and vacuum distillation unit in the t-th sub-cycle. This represents the yield of wax oil produced from the j-th crude oil in the m-th atmospheric and vacuum distillation unit; This represents the total quantity of wax oil produced by the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle; in formula (20) This represents the quantity of wax oil produced by the m-th atmospheric and vacuum distillation unit when producing the n-th type of residue oil in the t-th sub-cycle; Formula (21) limits the upper and lower limits of wax oil production, where and These represent the upper and lower limits of the wax oil production capacity of the m-th atmospheric and vacuum distillation unit, respectively.

[0111] (6) Scheme switching constraints:

[0112] (twenty two)

[0113] (twenty three)

[0114] Formulas (22)-(23) are used to determine whether the formula has changed. Let j be a binary variable between 0 and 1. If j is the type of crude oil supplied to the atmospheric and vacuum distillation unit in the t-th sub-cycle, then this term is 1; otherwise, it is 0. The variable is a binary variable of 0 and 1, which means that if the connection between the j-th crude oil and the m-th atmospheric and vacuum distillation unit changes between the t-1 and t-th sub-cycles, then this term is 1, and otherwise it is 0.

[0115] Specifically, in this embodiment of the application, a first objective function for long-term scheduling optimization will also be set, as shown below:

[0116] (twenty four)

[0117] Formula (24) above represents minimizing the total number of refining scheme switching operations for the atmospheric and vacuum distillation unit during the entire scheduling period, where , , and These represent the total cost over the entire scheduling cycle, the feed cost of the atmospheric and vacuum distillation unit, the crude oil formulation switching cost, and the ship's waiting and unloading costs at sea, respectively. This indicates the maximum oil inlet flow rate of the m-th atmospheric and vacuum distillation unit per day; This represents the feed rate of the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle; Indicates the number of times the crude oil formula has been switched; Indicates the time when the ship's crude oil unloading was completed; This indicates the arrival time of the crude oil transported by the ship.

[0118] In summary, the embodiments of this application can transform the resource allocation problem in crude oil scheduling into a solvable optimization problem through predefined constraints and objective functions.

[0119] Step 102: Based on long-term scheduling and production data, solve the long-term scheduling optimization model to generate a long-term scheduling scheme.

[0120] In this embodiment of the application, after determining the long-term scheduling and production data, the long-term scheduling optimization model can be solved using these data to generate a long-term scheduling scheme.

[0121] In one possible implementation, embodiments of this application can determine the mathematical representation corresponding to the long-term scheduling optimization model through long-term scheduling data, and solve the optimal solution of its mathematical representation according to a preset solver to obtain a long-term scheduling optimization scheme.

[0122] Specifically, the solution process for the long-term scheduling optimization model in this application includes: converting long-term scheduling data into a mathematical representation that the model can process, such as defining decision variables (e.g., continuous variables such as tanker unloading volume, crude oil tank inventory, and unit feed volume in each sub-cycle, as well as binary variables such as formula switching flags), setting constraints (e.g., material balance constraints, upper and lower limits of tank inventory, atmospheric and vacuum unit feed constraints, output constraints, and scheme switching constraints), and an objective function (with minimizing the number of refining scheme switching as the core, while taking into account feed costs and ship waiting costs). Furthermore, the constructed mixed-integer linear programming problem is solved using a pre-set optimization solver (e.g., the CPLEX solver), and the optimal solution is iteratively searched using algorithms such as branch and bound to ensure that the scheme minimizes the number of refining scheme switching while satisfying all constraints. Thus, the generated long-term scheduling scheme represents the optimal result of resource planning at this first time scale, and clarifies the total processing volume of the atmospheric and vacuum unit, crude oil formula composition, and residual oil production allocation in each sub-cycle, providing a global boundary and guiding framework for short-term scheduling.

[0123] Step 103: Based on the preset short-term scheduling optimization model, obtain the short-term scheduling data corresponding to the crude oil production process.

[0124] In this embodiment, the short-term scheduling optimization model is used to schedule crude oil operations on a second time scale (e.g., day or hour), which is smaller than the first time scale of the long-term model. This allows the long-term plan to be decomposed into executable operational instructions. The short-term scheduling production data represents the resource planning and operational scheduling data of crude oil at the second time scale. It includes not only basic data such as scheduling time cycle, incoming vessel plans, tank farm information, crude oil information, and atmospheric and vacuum distillation unit processing information, but also inherits the long-term scheduling plan as input conditions to ensure the coordination between planning and execution.

[0125] Specifically, in the embodiments of this application, the process of acquiring long / short-term scheduling production data can be refined according to the model requirements. For example, the ten-day plan can be decomposed into daily oil delivery allocation and real-time operating parameters (e.g., current tank farm inventory and equipment status) can be incorporated to enhance the dynamics and operability of the data, provide refined data support for operational scheduling, and achieve a smooth transition from resource planning to operation execution.

[0126] In one possible implementation, the short-term scheduling optimization model in this application embodiment can be constructed through the following steps:

[0127] The operational constraints and second objective function of the short-run scheduling optimization model are obtained, and the model is constructed using these constraints and objective function. The operational constraints of the short-run scheduling optimization model include at least one of the following: unloading operation constraints between the tanker and the crude oil tank; crude oil tank selection constraints; and feeding relationship constraints between the crude oil tank and the atmospheric and vacuum distillation unit. The second objective function is used to minimize the number of crude oil tank feeding switching operations.

[0128] Specifically, the constraints of the short-term scheduling optimization model in this application embodiment may include the resource constraints of the long-term scheduling optimization model, such as the aforementioned expressions (1)-(6), as well as the operational constraints of the short-term scheduling optimization, such as the unloading operation constraints between the tanker and the crude oil tank, the crude oil tank selection constraints, and the feeding relationship constraints between the crude oil tank and the atmospheric and vacuum distillation unit, as shown below:

[0129] (1) Restrictions on the unloading operations between oil tankers and crude oil tankers, including:

[0130] a. In a single cycle, a crude oil tank can only receive one type of crude oil from a single tanker:

[0131] (25)

[0132] b. In one sub-cycle, an oil tanker can unload oil into a maximum of two crude oil tanks:

[0133] (26)

[0134] c. While receiving crude oil, the crude oil tank must not transfer oil to the atmospheric and vacuum distillation unit:

[0135] (27)

[0136] Among them, in formula (25) It is a binary variable of 0 and 1. If the vth oil tanker unloads the jth type of crude oil into the kth oil tank in the tth sub-cycle, then this term is 1, otherwise it is 0.

[0137] In formula (27) It is a binary variable of 0 and 1. If the k-th oil tank supplies oil to the m-th atmospheric and vacuum distillation unit in the t-th sub-cycle, then this term is 1, otherwise it is 0.

[0138] (2) Crude oil tank selection constraints, including:

[0139] a. Prioritize unloading crude oil into empty tanks;

[0140] b. When constraint a is not satisfied, select the oil tank with high similarity as the oil receiving tank:

[0141] (28)

[0142] Among them, in formula (28) This indicates the similarity in the type of residual oil produced between crude oil j unloaded from the vth oil tanker and the bottom oil in crude oil tank k. Indicates the first The types of residual oil that can be produced from crude oil; and These represent the types of crude oil unloaded from the v-th ship and the types of crude oil at the bottom of the k-th crude oil tank, respectively.

[0143] c. Among the oil tanks with the highest similarity, select the oil tank with the largest unloading capacity;

[0144] (3) Constraints on the supply relationship between the crude oil tank and the atmospheric and vacuum distillation unit, including:

[0145] a. A single crude oil tank can supply oil to a maximum of two atmospheric and vacuum distillation units simultaneously:

[0146] (29)

[0147] b. Limit on the maximum number of crude oil tanks that a single atmospheric and vacuum distillation unit can simultaneously receive:

[0148] (30)

[0149] c. Limitation on the rate of crude oil transfer from the crude oil tank to the atmospheric and vacuum distillation unit:

[0150] (31)

[0151] The above formulas (29)-(31) determine the oil dispensing relationship between the atmospheric and vacuum distillation unit and the crude oil tank; among which, It is a binary variable of 0 and 1. If the k-th crude oil tank supplies oil to the m-th atmospheric and vacuum distillation unit, then this term is 1, otherwise it is 0. This indicates the maximum number of crude oil tanks that a single atmospheric and vacuum distillation unit can simultaneously receive oil from; This represents the minimum oil delivery rate from the k-th crude oil tank to the m-th atmospheric and vacuum distillation unit in each sub-cycle; This represents the maximum oil inlet flow rate of the m-th atmospheric and vacuum distillation unit in each sub-cycle.

[0152] Furthermore, this application embodiment will also set a second optimization objective function for the short-term scheduling optimization model, as shown below.

[0153] (32)

[0154] Formula (32) above represents minimizing the total number of crude oil tank feeding switches during the entire scheduling period of the atmospheric and vacuum distillation unit, where, This represents the number of times the crude oil tank feed is switched at the end of the t-th sub-cycle for the m-th atmospheric and vacuum distillation unit.

[0155] Step 104: Based on the preset hybrid optimization algorithm, and combining short-term scheduling data and long-term scheduling scheme, solve the short-term scheduling optimization model to generate a short-term scheduling scheme.

[0156] In this embodiment, after long-term scheduling optimization is completed, the scheduling scheme obtained from the long-term scheduling optimization is used as input. Based on the decomposition of the long-term scheduling optimization scheme, the short-term scheduling optimization sub-model is optimized, with the optimization objective being to minimize the number of crude oil tank supply switching operations. The hybrid optimization algorithm integrates evolutionary optimization algorithms (e.g., particle swarm optimization) and mathematical programming methods, thereby efficiently handling discrete decision variables (such as the selection of oil tanks) and continuous variables (such as the amount of oil supplied). The short-term scheduling scheme represents the crude oil scheduling scheme with the minimum number of crude oil tank supply switching operations at the second time scale, thus indicating the oil supply sequence and amount from each crude oil tank to the atmospheric and vacuum distillation unit in each sub-cycle, in order to improve operational efficiency and reduce production fluctuations.

[0157] In one possible implementation, the present application embodiment can perform population initialization based on short-term scheduling data to generate individual codes. These individual codes represent the selection of auxiliary oil tanks and the allocation of auxiliary oil volume for each sub-cycle. The selection of auxiliary oil tanks is iteratively optimized using a particle swarm optimization algorithm, and the auxiliary oil volume for each auxiliary oil tank is determined using a mathematical programming method to generate a short-term scheduling scheme.

[0158] For details, please refer to Figure 2 The diagram illustrates the processing flow of a hybrid optimization algorithm provided in this embodiment. The solution process for the short-term scheduling optimization model in this embodiment may include initializing algorithm parameters (such as population size and maximum evaluation count), performing population initialization to generate individual codes representing tank selection and fuel allocation, optimizing the coding portion of integer variables using a large-scale particle swarm optimization algorithm to search for the optimal tank combination, and solving the continuous variable portion using mathematical programming to accurately calculate the optimal fuel allocation for each tank. If the optimization result does not meet the constraints, it is considered an infeasible solution. A genetic algorithm is then used to correct the fuel allocation (such as mutation, crossover, and selection operations), and the above operations are repeated until the maximum number of iterations is reached, outputting the optimal solution and generating a short-term scheduling scheme. Thus, through evolutionary optimization and mathematical programming, a complex optimization problem involving a mixture of discrete and continuous variables is effectively solved.

[0159] For details, please refer to Figure 3The diagram shows an individual coding scheme provided in an embodiment of this application. The coding for one sub-cycle consists of two parts: the receiving tank code and the auxiliary tank code. The receiving tank code includes the receiving tank number corresponding to each tanker v in two consecutive sub-cycles, denoted as RTv,1 and RTv,2, used to determine the target tank for tanker unloading operations. The auxiliary tank code sets coded bits for each atmospheric and vacuum distillation unit (e.g., units 1 to m). For example, CTm,1 to CTm,5 represent the five auxiliary tank numbers that the m-th unit can connect to within the same sub-cycle. Each pair of coded bits represents the receiving tank number selected in a sub-cycle. This design directly corresponds to the constraint on the maximum number of auxiliary tanks connected to the unit in the model. In the auxiliary tank code, each coded bit represents the auxiliary tank number selected by a certain atmospheric and vacuum distillation unit in the same sub-cycle, and is also related to the constraints of the atmospheric and vacuum distillation unit and the maximum number of auxiliary tanks connected as defined in the aforementioned formula (30). In this way, the scheduling decision variables (selection of receiving tanks and allocation of dispatching tanks) are transformed into a numerical sequence that can be processed by the optimization algorithm through the coding structure, providing a structured representation basis for the initial population of subsequent particle swarm optimization and genetic algorithm.

[0160] Specifically, the hybrid optimization algorithm based on long-term scheduling scheme decomposition in this application embodiment may include the following steps:

[0161] (1) Initialize the parameters of the evolutionary optimization algorithm: set the population size and the maximum number of evaluations.

[0162] (2) Population initialization, as follows:

[0163] a. Individual codes are constructed based on the decision variables in the short-term scheduling optimization model;

[0164] b. Initialize the oil tanks and oil quantities for each sub-cycle for each individual, and add the initialized individuals to the initialization population. The calculation formula is as follows:

[0165] (33)

[0166] (34)

[0167] Among them, in formula (33) This indicates the s-th crude oil tank that supplies oil to the m-th atmospheric and vacuum distillation unit during the t-th sub-cycle. Let represent the set of crude oil tanks that can supply oil to the m-th atmospheric and vacuum distillation unit at the t-th position, and randi denotes a random selection operation based on a uniform distribution. This represents the set of oil tanks that the atmospheric and vacuum distillation unit can receive; in formula (34) This represents the random number representing the amount of oil supplied to the s-th oil tank of the m-th atmospheric and vacuum distillation unit during the t-th sub-cycle, and rand represents a random number generated uniformly within the range [0,1]. This represents the amount of oil supplied from the s-th oil tank to the m-th atmospheric and vacuum distillation unit during the t-th sub-cycle.

[0168] c. If the total number of individuals in the population does not meet the population size requirement, repeat step b; otherwise, terminate.

[0169] (3) Set the fitness function;

[0170] (35)

[0171] (36)

[0172] (37)

[0173] Among them, in formula (35) and Let represent inequality constraints and equality constraints, respectively. If the solution x does not satisfy the i-th inequality or equality constraint, then... ;on the contrary, Therefore, the fitness value of individual x is denoted as (obj(x), cv(x)), where obj(x) represents the objective value of solution x, and cv(x) represents the sum of constraint violations. and If formula (37) is satisfied, then the solution is... Its fitness is better than .

[0174] (4) The initial population is iteratively optimized using a hybrid optimization algorithm that combines evolutionary optimization with mathematical programming. The specific steps are as follows:

[0175] a. For the selection of auxiliary oil tanks in each sub-cycle, a large-scale particle swarm optimization algorithm is used to optimize and update the velocity and position of the particles. The update formula is as follows:

[0176] (38)

[0177] (39)

[0178] Among them, in formula (38) Indicates the inertial weight, which controls the influence of the particle's current velocity on its next velocity; and This represents the learning factor, which controls the intensity of a particle's movement toward itself or the global optimal position. and Represents a random number between [0, 1]. and Let these represent the velocity of the i-th particle in the j-th dimension at the t-th and t+1-th iterations, respectively. and Let represent the individual optimal position of the i-th particle up to the t-th iteration and the global optimal position of all particles up to the t-th iteration, respectively; in formula (39) and This represents the position of the i-th particle in the j-th dimension during the t-th and t+1-th iterations;

[0179] b. To improve the efficiency of solving continuous variables, this application embodiment will use mathematical programming to determine the amount of oil dispensed from the oil tank in each sub-cycle. The mathematical expression of this optimization problem is as follows:

[0180] (40)

[0181] The objective of formula (40) above is to minimize the deviation between the actual amount of each type of oil dispensed and the planned amount of oil dispensed in the planned formula. , and These represent the initial volume, the volume of oil dispensed, and the lower limit volume of the storage capacity of the k-th oil tank, respectively.

[0182] In summary, in this embodiment of the application, if the optimization algorithm has not reached the maximum number of evaluations, the above steps ab will be repeated; otherwise, the process will end.

[0183] In one possible implementation, during the iterative optimization of oil tank selection using the particle swarm optimization algorithm, if the optimization result output by the iterative optimization is an infeasible solution, the feed formula can be modified by a preset genetic algorithm to obtain a modified short-term scheduling scheme.

[0184] Specifically, this application embodiment considers that limitations such as the capacity and number of storage tanks may prevent resource planning from being decomposed into operation scheduling. If the optimization result obtained by the aforementioned hybrid optimization algorithm is an infeasible solution, this application will further employ a genetic algorithm to modify the feed formulation, with the specific steps as follows:

[0185] (1) Initialize the parameters and population. This step is the same as the steps in the previous embodiment, and will not be repeated here.

[0186] (2) For the amount of oil dispensed in each sub-cycle, a genetic algorithm is used for optimization. The formulas for mutation, crossover, and selection operations are as follows:

[0187] (41)

[0188] Formula (41) uses Gaussian mutation to add a Gaussian noise to the genes of each individual. That is, from a mean of 0 and a variance of Random values ​​obtained by sampling from a normal distribution.

[0189] (42)

[0190] Formula (42) uses uniform crossover to randomly determine which parent's gene the offspring inherited at each locus. It is a randomly generated value that determines which parent the gene at that position comes from. and Let represent the genes at position j in parent generation p and parent generation q, respectively.

[0191] (43)

[0192] In formula (43) This represents the fitness function value of the solution vector x;

[0193] (3) If the algorithm has not reached the maximum number of evaluations, repeat step (2) above; otherwise, end the process and output a short-term crude oil scheduling scheme that minimizes the number of crude oil tank supply switching operations.

[0194] Thus, this application embodiment, through a hierarchical model structure, effectively connects long-term resource planning with short-term operational execution, solving the problem of disconnect between planning and scheduling in traditional methods, and improving the overall integrity and executability of the scheduling scheme. Furthermore, this application embodiment also improves the solution efficiency of large-scale scheduling problems by combining a hybrid optimization algorithm of mathematical programming and evolutionary optimization, enabling the generation of optimized scheduling schemes within a reasonable timeframe. Further, this application embodiment aims to minimize the number of refining scheme switching times and crude oil tank feeding switching times, reducing frequent adjustments during production, lowering operational complexity, and improving equipment stability. Moreover, the scheduling optimization method provided by this application embodiment is highly adaptable, capable of handling complex scenarios involving multiple oil types and multiple tank areas, providing a systematic solution for refining and chemical enterprises, and helping to achieve cost reduction, efficiency improvement, and quality enhancement.

[0195] In one possible implementation, refer to Figure 4 The diagram shown is a schematic representation of a crude oil dispatching process in a refining and chemical enterprise, as provided in an embodiment of this application. Figure 4This demonstrates the complete oil refining process. Tankers transport crude oil to a crude oil tank farm for temporary storage. The crude oil then enters an atmospheric and vacuum distillation unit for processing, producing intermediate products including wax oil, naphtha, kerosene, diesel, wash oil, and residue oil. These products are distributed to different storage areas within the intermediate product tank farm. The wax oil tank farm is further subdivided into sulfur-containing and low-sulfur storage areas, while the residue oil tank farm includes dedicated storage areas for coking, catalytic cracking, asphalt, and residue processing. This application's embodiments utilize a multi-timescale collaborative optimization model for long-term and short-term scheduling to optimize the crude oil receiving, storage, processing, and product distribution stages of the above process. Long-term scheduling plans resources (e.g., tanker arrival schedules and tank farm inventory) on a ten-day / monthly basis, while short-term scheduling refines operations on a daily / hourly basis (e.g., auxiliary tank selection and feed sequence). This ensures the efficient operation of the entire process and minimizes the number of refining scheme switching and crude oil tank feed switching operations.

[0196] Next, this application will take the crude oil scheduling process of a large-scale refining and chemical enterprise as an example to specifically introduce the scheduling optimization method of this application:

[0197] refer to Figures 5-10 The diagrams shown are schematic representations of tanker information, initial crude oil tank information, initial wax residue oil tank information, atmospheric and vacuum distillation unit processing data, crude oil property information, and crude oil yield information provided in this application embodiment. The total scheduling time for this application embodiment is 10 days (one day is a scheduling sub-cycle), including 7 tankers (unloading rate of 5000 t / h), 18 crude oil tanks, 3 atmospheric and vacuum distillation units, 5 types of atmospheric and vacuum distillation unit side-stream products (naphtha, atmospheric first-line product, diesel, wax oil, and wash oil), 2 types of wax oil tanks (sulfur-containing wax oil and low-sulfur wax oil), and 4 residue oil tanks (coking feed, asphalt feed, catalyst feed, and residue feed). This application embodiment obtains the above... Figures 1-6 The tanker data shown can be imported into a pre-established long-term scheduling optimization model, and the CPLEX solver can be used to solve the long-term scheduling optimization model to verify its practicality and effectiveness, and output a long-term scheduling optimization scheme that minimizes the number of refining formula switching.

[0198] For details, please refer to Figure 11The diagram illustrates a long-term scheduling scheme provided in an embodiment of this application. The diagram displays the optimized long-term scheduling scheme in tabular form, including information such as unit number, processing start and end cycles / day, processing load / ton, type of residual oil produced, and component oil ratio. Taking unit CDU1 as an example, its processing load is 21,000 tons in a 1-2 day cycle, producing coking feedstock with a component oil ratio of C8:C12:C5:C4 (5.7:1.9:1.3:1). In a 2-10 day cycle, its processing load is 156,420 tons, producing asphalt feedstock with a component oil ratio of C12:C8:C5:C4 (5.6:2:1.4:1). Thus, this long-term scheduling scheme demonstrates the goal of minimizing the number of refining scheme switching times on a daily timescale. By clearly defining the processing load, residual oil type, and component oil ratio of each unit, it provides an executable resource planning framework for short-term scheduling.

[0199] Furthermore, in this embodiment, based on a pre-constructed short-term scheduling optimization sub-model, the scheduling time period, incoming vessel schedule, crude oil tank area, wax oil tank area, and residual oil tank area information, crude oil information, and atmospheric and vacuum distillation unit processing information are set to obtain corresponding short-term scheduling data. A discrete-time representation method is used to divide the entire scheduling cycle into multiple sub-cycles with the same time length, thereby decomposing the produced long-term scheduling optimization scheme. A hybrid optimization algorithm is then used to solve the short-term scheduling optimization sub-model to obtain a short-term crude oil scheduling scheme that minimizes the number of crude oil tank supply switching operations.

[0200] For details, please refer to Figure 12 The diagram shown is a schematic representation of a short-term scheduling scheme provided in an embodiment of this application. Figure 13 This is a Gantt chart diagram illustrating a short-term crude oil dispatching scheme provided in an embodiment of this application. Figure 12 The chart displays the detailed operational schedule over a 10-day period obtained from the short-term scheduling model, involving three atmospheric and vacuum distillation units (CDU1, CDU2, and CDU3). The horizontal axis represents the time period from 0 to 10 days, and the vertical axis represents the daily combination of operating units and the throughput for each unit. Taking CDU1 as an example, it is operated solely by T15 on days 0-1, with a throughput of 16.11 thousand tons / day. Subsequently, on days 1-2, it is adjusted to operate in a coordinated manner with T2, T6, and T15 in a ratio of 1:2.3:6.8, with a throughput of 14.46 thousand tons / day. In subsequent days, the combinations are switched sequentially, such as T1:T2:T5:T6, T6, T5:T14:T18, etc., with daily throughputs marked as 13.17 thousand tons / day, 15.99 thousand tons / day, etc. Figure 13This diagram illustrates the oil receiving and discharging operations of 18 crude oil tanks (T1 to T18) within a 10-day scheduling cycle. Dark gray bars represent "oil receiving volume," labeled with oil type (e.g., C2, C11), while light gray bars represent "oil discharging volume," specifying the amount discharging to atmospheric and vacuum distillation units #1, #2, or #3. For example, "7255 (2#)" in row T1 indicates a discharging of 7255 tons to unit #2, and "discharging volume (1#)" indicates the discharging volume to unit #1. This Gantt chart visualizes the short-term scheduling model obtained through a hybrid optimization algorithm in this embodiment. It demonstrates that by minimizing the number of crude oil tank supply switching operations, and by precisely planning the daily material inflow (oil receiving) and outflow (oil discharging) sequence for each crude oil tank, the feasibility and efficiency of the operation scheduling are ensured. In the above short-term scheduling scheme, the optimal number of switching times for the crude oil tanks feeding the atmospheric and vacuum distillation unit is 19, the average running time of the algorithm is 300 seconds, and by accurately planning the daily activation combination, ratio and processing load of the auxiliary oil tanks (represented by tower number) of each unit, the goal of minimizing the number of switching times for crude oil tank feeding is achieved, ensuring the feasibility and efficient execution of the long-term scheduling scheme at the operational level.

[0201] Please see Figure 14 As shown, based on the same technical concept, this application also provides a computer device 140. In one embodiment, the computer device can be a device specifically for crude oil production scheduling and control, or it can be a device for overall control of industrial production. The computer device, as shown... Figure 14 As shown, it includes a memory 1401, a communication module 1403, and one or more processors 1402.

[0202] The memory 1401 is used to store computer programs executed by the processor 1402. The memory 1401 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0203] Memory 1401 may be volatile memory, such as random-access memory (RAM); memory 1401 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 1401 may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 1401 may be a combination of the above-described memories.

[0204] Processor 1402 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 1402 is used to implement the above-described crude oil scheduling optimization method when calling the computer program stored in memory 1401.

[0205] The communication module 1403 is used to communicate with the industrial control system.

[0206] This application embodiment does not limit the specific connection medium between the memory 1401, communication module 1403, and processor 1402. This application embodiment... Figure 14 The memory 1401 and the processor 1402 are connected via a bus 14014, and the bus 14014 is in Figure 14 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. The 14014 bus can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 14 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.

[0207] The memory 1401 stores a computer storage medium, which stores computer-executable instructions. The computer-executable instructions are used to implement the crude oil scheduling optimization method of the embodiments of this application, and the processor 1402 is used to execute the crude oil scheduling optimization methods of the above embodiments.

[0208] Based on the same inventive concept, embodiments of this application also provide a storage medium storing a computer program that, when run on a computer, causes the computer to execute the steps in the crude oil scheduling optimization method according to various exemplary embodiments of this application described above.

[0209] In some possible implementations, various aspects of the crude oil dispatch optimization method provided in this application can also be implemented in the form of a computer program product, which includes a computer program. When the program product is run on a computer device, the computer program is used to cause the computer device to perform the steps in the crude oil dispatch optimization method according to various exemplary embodiments of this application described above. For example, the computer device can perform the steps of each embodiment.

[0210] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0211] The program product of the embodiments of this application may employ a portable compact disc read-only memory (CD-ROM) and include a computer program, and may run on a computer device. However, the program product of this application is not limited thereto. In this application, the readable storage medium may be any tangible medium that contains or stores a program, and the computer program included therein may be used by or in conjunction with a command execution system, apparatus, or device.

[0212] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a readable computer program. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with a command execution system, apparatus, or device.

[0213] Computer programs contained on readable media may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0214] Computer programs for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages.

[0215] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0216] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0217] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0218] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0219] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A crude oil scheduling optimization method characterized by, The method comprises: obtaining long-term scheduling production data corresponding to the crude oil production process based on a preset long-term scheduling optimization model; the long-term scheduling optimization model is used for resource planning of the crude oil in a first time scale, and the long-term scheduling production data represents resource planning data and operation scheduling data of the crude oil production process in the first time scale; solving the long-term scheduling optimization model based on the long-term scheduling production data to generate a long-term scheduling scheme; the long-term scheduling scheme represents a crude oil scheduling scheme with the minimum number of refinery scheme switching times in the first time scale; obtaining short-term scheduling production data corresponding to the crude oil production process based on a preset short-term scheduling optimization model; the short-term scheduling optimization model is used for operation scheduling of the crude oil in a second time scale, the first time scale is greater than the second time scale, and the short-term scheduling production data represents resource planning data and operation scheduling data of the crude oil in the second time scale; solving the short-term scheduling optimization model based on a preset hybrid optimization algorithm, combining the short-term scheduling production data and the long-term scheduling scheme to generate a short-term scheduling scheme; the short-term scheduling scheme represents a crude oil scheduling scheme with the minimum number of crude oil tank feed switching times in the second time scale.

2. The method of claim 1, wherein, The long-term scheduling optimization model is constructed based on the following steps: obtaining resource constraints and a first optimization objective function of the long-term scheduling optimization model; the long-term constraints include at least one of material balance constraints, upper and lower limit constraints of tank inventory, CDU feed constraints, CDU output constraints, wax residue oil yield constraints and scheme switching constraints, and the first optimization objective function is used to minimize the total number of refinery scheme switching times; constructing the long-term scheduling optimization model based on the resource constraints and the first optimization objective function.

3. The method of claim 1, wherein, The short-term scheduling optimization model is constructed based on the following steps: obtaining operation constraints and a second optimization objective function of the short-term scheduling optimization model; the operation constraints include at least one of unloading operation constraints between oil tankers and crude oil tanks, crude oil tank selection constraints, and feed relationship constraints between crude oil tanks and CDUs, and the second optimization objective function is used to minimize the number of crude oil tank feed switching times; constructing the short-term scheduling optimization model based on the operation constraints and the second optimization objective function.

4. The method of claim 1, wherein, The solving of the long-term scheduling optimization model based on the long-term scheduling production data to generate a long-term scheduling scheme comprises: determining the mathematical representation corresponding to the long-term scheduling optimization model based on the long-term scheduling production data; obtaining the long-term scheduling scheme by solving the mathematical representation based on a preset solver.

5. The method of claim 1, wherein, The solving of the short-term scheduling optimization model based on a preset hybrid optimization algorithm, combining the short-term scheduling production data and the long-term scheduling scheme to generate a short-term scheduling scheme comprises: performing population initialization based on the short-term scheduling production data to generate individual codes, the individual codes representing oil tank selection and oil allocation of each sub-period; The particle swarm optimization algorithm is used to iteratively optimize the oil tank selection, and a mathematical programming method is used to determine the oil loading of each oil tank to generate the short-term scheduling scheme.

6. The method of claim 5, wherein, The particle swarm optimization algorithm is used to iteratively optimize the oil tank selection, and a mathematical programming method is used to determine the oil loading of each oil tank to generate the short-term scheduling scheme. When the optimization result output by the iterative optimization is an infeasible solution, a preset genetic algorithm is used to correct the feed formula to obtain a corrected short-term scheduling scheme.

7. The method of claim 1, wherein, The long-term scheduling production data and the short-term scheduling production data correspond to scheduling production data sets in the first time scale and the second time scale, respectively; the scheduling production data set includes scheduling time period, ship arrival plan, tank farm information, crude oil information, and atmospheric-vacuum distillation unit processing information; the ship arrival plan includes tanker arrival time, oil carrying capacity, and oil unloading rate; the tank farm information includes the number of oil tanks in the crude oil tank farm, the wax oil tank farm, and the residual oil tank farm, the initial inventory, and the upper and lower limits of the inventory; the crude oil information includes crude oil attribute values, yield, and produced wax and residual oil types; and the atmospheric-vacuum distillation unit processing information includes feed upper and lower limits and attribute upper and lower limits. 8.A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 7. 9.A computer storage medium having computer program instructions stored thereon, wherein, The computer program instructions are executed by the processor to implement the steps of the method of any one of claims 1 to 7. 10.A computer program product, comprising computer program instructions, wherein, The computer program instructions are executed by the processor to implement the steps of the method of any one of claims 1 to 7.

Images