A method, system and device for adjusting a refinery scheduling scheme

Abstract

This application belongs to the field of refinery production scheduling technology, and discloses a method, system, and apparatus for adjusting a refinery production scheduling plan. The method includes obtaining an initial refinery production scheduling plan; selecting target tanks in the initial production scheduling plan that do not meet preset tank storage constraints; and adjusting the feed and discharge plans of each target tank until a refinery production scheduling plan is obtained in which no target tank exceeds the upper or lower limit of oil volume. The adjustment method of this application can mimic the thinking of production schedulers in adjusting production scheduling plans. Based on the initial production scheduling plan given by scheduling optimization software, it intelligently replaces the parts that originally required manual adjustment and early warning elimination by schedulers, automatically adjusts the initial production scheduling plan, eliminates early warnings, directly provides feasible scheduling plans for production schedulers, accumulates scheduling experience, and improves work efficiency.

Description

Technical Field

[0001] This application belongs to the field of refinery production scheduling technology, and in particular relates to a method, system and apparatus for adjusting refinery production scheduling schemes. Background Technology

[0002] Currently, intelligent scheduling software used in the industry for refinery production scheduling mainly employs two technical approaches: operations research optimization and simulation. In operations research optimization, due to the possibility of relaxation during the optimization solution process, the initial production scheduling plan needs to be simulated to verify whether it meets constraints such as tank storage. If not, the software issues a warning, and schedulers then manually adjust it to obtain a feasible production scheduling plan. Therefore, the initial production scheduling plan may not necessarily meet scheduling constraints and lacks feasibility, requiring further manual adjustments.

[0003] However, the tank inventory constraint is a physical constraint that the scheduler is very concerned about and must satisfy. This requires that when the tank inventory constraint exceeds the limit, the model structure or other constraints need to be manually adjusted to obtain a feasible scheduling scheme. Summary of the Invention

[0004] In order to overcome the shortcomings of the existing technology, this application provides a method, system and apparatus for adjusting refinery production scheduling.

[0005] To achieve the above objectives, this application provides the following technical solution:

[0006] A method for adjusting a refinery production scheduling plan includes:

[0007] Obtain the initial production schedule from the refinery;

[0008] Select the target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints;

[0009] Adjust the feed and discharge plans for each target tank until a refinery production schedule is obtained that does not have any target tanks with oil volumes exceeding the upper or lower limits.

[0010] Furthermore, obtain the refinery's initial production scheduling plan, including:

[0011] A scheduling model is established based on the refinery's units, tank areas, and material flow. Unit load, scheme selection, and material flow are used as decision variables, while material balance, unit yield, load upper and lower limits, tank capacity upper and lower limits, and scheduling rules are used as constraints. The objective function is to minimize the scheduling operation cost. A mixed integer programming solution is then performed, and the solution is the initial production scheduling scheme for the refinery.

[0012] Furthermore, adjust the feeding and discharging schemes for each target tank, including:

[0013] Adjust the oil volume in the target tank by adjusting at least one of the following:

[0014] The number of upstream units of the target tank as the receiving tank;

[0015] The output of the upstream unit;

[0016] The number of downstream units supplied by the target tank;

[0017] Feed rate to downstream unit;

[0018] The number of oil tanks receiving the oil being poured from the target tank;

[0019] The number of oil tanks to be poured into the target tank.

[0020] Furthermore, adjust the feeding and discharging schemes for each target tank, including:

[0021] The number of upstream devices serving as oil receiving tanks and the number of downstream devices supplying oil to the target tanks are adjusted through tank-cutting operations.

[0022] The discharge rate of the upstream unit and the feed rate of the downstream unit are adjusted by regulating the load operation of the units.

[0023] The quantity of oil received from the target tank or oil poured into the target tank is adjusted by the tank transfer mechanism.

[0024] Furthermore, adjust the feeding and discharging schemes for each target tank, including:

[0025] Adjust the oil volume in the target tank according to the operational sequence of switching the receiving tank, transferring the oil, switching the auxiliary tank, and adjusting the load of the equipment.

[0026] Furthermore, adjust the feeding and discharging schemes for each target tank, including:

[0027] The oil tanks or devices corresponding to each operation, such as switching the receiving oil tank, transferring the oil tank, switching the auxiliary oil tank, and adjusting the load of the device, are scored in sequence.

[0028] If there is a non-zero score among the tanks or devices in the current operation's evaluation, the tank or device with the highest score shall be the preferred option for the current operation.

[0029] When the scores of the oil tank or device corresponding to the current operation are all 0, the oil tank or device corresponding to the next operation is scored.

[0030] When the score of the oil tank or device corresponding to each operation is 0, the temporary emergency tank is activated to adjust the oil volume of the target tank.

[0031] Furthermore, the formula for calculating the score is as follows:

[0032] S = a * b

[0033] a = 10c / d

[0034] Where S is the score of the oil tank or device corresponding to the target tank in the current operation; a is the operation probability score; b is the operation convenience score, which is a constant determined based on the following: the number of adjustments required to adjust the oil volume of the target tank to no longer exceed the upper or lower limit using the oil tank or device currently being scored; c is the number of topological connections from the target tank to the oil tank or device currently being scored in the historical data; and d is the highest number of topological connections from all oil tanks or devices to be scored to the target tank in the historical data.

[0035] This application also discloses a refinery production scheduling adjustment system, including:

[0036] The initial module is used to obtain the initial production schedule of the refinery;

[0037] The selection module is used to select target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints.

[0038] The adjustment module is used to adjust the feeding and discharging schemes of each target tank until a refinery production schedule is obtained for target tanks where no oil volume exceeds the upper or lower limit.

[0039] This application also discloses an electronic device, including a memory and a processor, wherein the memory stores a computer program or instructions, and when the computer program or instructions are executed by the processor, they are used to implement at least the above-described method.

[0040] This application also discloses a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, are at least used to implement the above-described method.

[0041] This application also discloses a computer program product stored in a computer-readable storage medium, which, when executed by a processor, is used to implement at least the above-described method.

[0042] The technical effects and advantages of this application are as follows:

[0043] This application obtains the initial production schedule of a refinery and determines whether the initial production schedule meets the preset tank storage constraints. If the initial production schedule does not meet the preset tank storage constraints, it selects the target tanks in the initial production schedule that do not meet the preset tank storage constraints, and adjusts at least one of the following: the quantity and amount of oil discharged from the upstream unit that uses the current target tank as an oil receiving tank; the quantity and amount of oil fed by the downstream unit that uses the current target tank as a receiving tank; and the number of oil tanks that receive or pour oil into the current target tank, until there are no target tanks with oil quantities exceeding the upper or lower limit. This results in an adjusted refinery production schedule, automating and intelligentizing the adjustment process of the initial production schedule, and providing dispatchers with feasible production schedules directly.

[0044] Other features and advantages of this application 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 application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for adjusting a refinery production scheduling scheme according to this application;

[0046] Figure 2 This is a schematic diagram of the material balance principle in an embodiment of this application;

[0047] Figure 3 This is a schematic diagram illustrating the operation sequence of receiving oil tank, transferring oil tank, receiving oil tank, and adjusting the load of the device according to an embodiment of this application.

[0048] Figure 4 This is a structural diagram of a refinery production scheduling adjustment system according to this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. 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.

[0050] like Figure 1 As shown, this application provides a method for adjusting a refinery production scheduling scheme, including:

[0051] Obtain the initial production schedule from the refinery;

[0052] Select the target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints;

[0053] Adjust the feed and discharge plans for each target tank until a refinery production schedule is obtained that does not have any target tanks with oil volumes exceeding the upper or lower limits.

[0054] The refinery production scheduling adjustment method proposed in this application can mimic the thinking of production schedulers when adjusting production scheduling plans. Based on the initial production scheduling plan given by the scheduling optimization software, it intelligently replaces the parts that originally required manual adjustment and warning elimination by schedulers, automatically adjusts the initial production scheduling plan, eliminates warnings, directly provides production schedulers with feasible scheduling plans, accumulates scheduling experience, and improves work efficiency.

[0055] In some embodiments of this application, obtaining the initial production scheduling plan for a refinery includes:

[0056] A scheduling model is established based on the refinery's units, tank areas, and material flow. Unit load, scheme selection, and material flow are used as decision variables, while material balance, unit yield, load upper and lower limits, tank capacity upper and lower limits, and scheduling rules are used as constraints. The objective function is to minimize the scheduling operation cost. A mixed integer programming solution is then performed, and the solution is the initial production scheduling scheme for the refinery.

[0057] Because refinery production scheduling is inherently a multi-objective, multi-constraint problem, and the initial production scheduling plan is solved based on a data programming model, it must be pre-defined with clear production processes and specific constraints. A medium-sized refinery's scheduling model may contain tens of thousands of constraint equations. To ensure solution performance, some constraints are always relaxed during the solution process. Since tank inventory changes are the easiest to observe and characterize, tank inventory is typically relaxed. Therefore, the initial refinery production scheduling plan may not meet the pre-set tank inventory constraints.

[0058] In some embodiments of this application, the oil volume in the target tank is adjusted by adjusting at least one of the following: the number of upstream devices that serve as the target tank as the receiving tank, the discharge rate of the upstream devices, the number of downstream devices that supply the target tank, the feed rate of the downstream devices, the number of oil tanks receiving oil from the target tank, and the number of oil tanks pouring oil into the target tank. The number of upstream devices that serve as the target tank as the receiving tank and the number of downstream devices that supply the target tank are adjusted by a tank-cutting operation; the discharge rate of the upstream devices and the feed rate of the downstream devices are adjusted by adjusting the load operation of the devices; and the number of oil tanks receiving oil from the target tank is adjusted by a tank-switching operation.

[0059] Specifically, for each target tank whose oil volume exceeds the upper limit in the initial production schedule of the refinery, the oil volume of the current target tank is adjusted by at least one of the following: reducing the number of upstream devices that use the current target tank as an oil receiving tank, reducing the discharge rate of the upstream devices, increasing the number of downstream devices that supply the current target tank, increasing the feed rate of the downstream devices, and increasing the number of tanks that receive oil dumped from the current target tank. For each target tank whose oil volume exceeds the lower limit in the initial production schedule of the refinery, the oil volume of the current target tank is adjusted by at least one of the following: increasing the number of upstream devices that use the current target tank as an oil receiving tank, increasing the discharge rate of the upstream devices, reducing the number of downstream devices that supply the current target tank, reducing the feed rate of the downstream devices, and reducing the number of tanks that receive oil dumped from the current target tank.

[0060] In some embodiments of this application, the tank inventory change of each tank in the refinery is calculated based on the refinery production process topology and material balance principles using the following expression:

[0061]

[0062] Where Δw is the change in the tank inventory of the target tank, w in w is the amount of material entering the target tank. out Let be the amount of material discharged from the target tank, i be the i-th upstream device that uses this tank as an oil receiving tank, and w be the amount of material discharged from the target tank. i，in For the oil received from the i-th upstream unit, n is the number of upstream units; j is the j-th oil tank (source tank) from which oil is poured to the target tank, w j，in For the amount poured into the j-th source tank, m is the number of source tanks; k is the k-th downstream device that needs to be supplied by the target tank, w k,out Let p be the oil supply amount for the k-th downstream unit, p be the number of downstream units, 1 be the first oil tank (destination tank) receiving oil from the target tank, and w be the oil supply amount for the k-th downstream unit. l,out q represents the amount poured out for the first destination container, and q represents the number of destination containers.

[0063] There are two scenarios for exceeding the storage limit: exceeding the upper limit and exceeding the lower limit. When exceeding the upper limit, it is necessary to automatically adjust and reduce Δw; when exceeding the lower limit, it is necessary to automatically adjust and increase Δw. The material balance principle is as follows: Figure 2 As shown. When the upper limit is exceeded, because the optimization model will minimize relaxation during calculation, it will prevent other source tanks from feeding oil into the target tank; therefore, w... j,in If the item does not exist, the change in tank inventory Δw of the target tank is calculated using the following expression:

[0064]

[0065] Depend on Figure 2 Considering the actual operation of the refinery, the following methods can be used to reduce Δw:

[0066] First, reduce n, that is, reduce the number of upstream units that use the target tank as the receiving tank. In the actual operation of the refinery, other tanks should be selected as receiving tanks and the tank switching operation should be carried out.

[0067] Second, reduce w i，in This means reducing the output of a certain upstream unit. For refinery operations, this requires lowering the load of the upstream unit. Since the optimization model minimizes relaxation, in the absence of other bottlenecks, the load of the upstream unit should already be at its lower limit. For refinery operations, it is necessary to select units whose loads may exceed the lower limit and perform load reduction operations, that is, automatically modify the unit load lower limit constraints in the model.

[0068] Third, increase p, which means increasing the number of downstream units that need to be supplied by the target tank. In actual refinery operations, the downstream units that were originally supplied by other tanks should be selected for tank switching operations.

[0069] Fourth, increase w k，outIn other words, increasing the feed rate to a downstream unit, corresponding to refinery operations, requires increasing the load on that downstream unit. Since the optimization model minimizes relaxation, in the absence of other bottlenecks, the load on the downstream unit should already be at its upper limit. For refinery operations, it is necessary to select units whose load might exceed the upper limit and increase their load accordingly, i.e., automatically modify the unit load upper limit constraints in the model.

[0070] Fifth, increase q, which means increasing the number of oil tanks (destination tanks) receiving oil from the target tank. In actual refinery operations, oil tanks with similar materials and interconnected processes should be selected as destination tanks for the transfer operation. The transfer volume is automatically balanced by the optimization model, so it is not considered as an operational adjustment.

[0071] When the lower limit is exceeded, the optimization model will minimize relaxation during calculation, preventing oil from being discharged from the target tank to other destination tanks. Therefore, w l，out If the item does not exist, the change in the tank inventory of the target tank is calculated using the following expression:

[0072]

[0073] Depend on Figure 2 Considering the actual operation of the refinery, there are several ways to increase Δw:

[0074] First, increase n, which means reducing the number of upstream units that use the target tank as an oil receiving tank. In actual refinery operations, other tanks should be selected as oil receiving tanks for tank switching operations.

[0075] Second, increase w i，in This means reducing the output of a certain upstream unit. For refinery operations, this requires lowering the load of the upstream unit. Since the optimization model minimizes relaxation, in the absence of other bottlenecks, the load of the upstream unit should already be at its lower limit. For refinery operations, it is necessary to select units whose loads may exceed the lower limit and perform load reduction operations, that is, automatically modify the unit load lower limit constraints in the model.

[0076] Third, increasing 'm', which represents increasing the number of oil tanks (source tanks) to be transferred to the target tank, in actual refinery operations, means selecting other tanks with similar materials and interconnected processes as source tanks for the transfer operation. The transfer volume w... j，in The balancing is performed automatically by the optimization model, so it is not considered an operational adjustment.

[0077] Fourth, reduce p, that is, reduce the number of downstream units that need to be supplied by the target tank. In the actual operation of the refinery, other tanks should be selected to supply the downstream units, and a tank switching operation should be carried out.

[0078] Fifth, reduce w j，inThis means reducing the feed rate to a downstream unit. In refinery operations, this requires reducing the load on the downstream unit. Since the optimization model minimizes relaxation, in the absence of other bottlenecks, the load on the downstream unit should already be at its lower limit. In refinery operations, this means selecting units whose loads might exceed the lower limit and performing load reduction operations, i.e., automatically modifying the unit load lower limit constraints in the model.

[0079] In some embodiments of this application, considering the cost and difficulty of operations such as switching in a receiving tank, transferring tanks, switching out a secondary tank, and adjusting the load of the device, in actual adjustments, such as... Figure 3 As shown in the flowchart, the oil volume in the target tank is adjusted according to the operation sequence of switching the receiving tank, transferring the oil, switching the auxiliary tank, and adjusting the load of the equipment.

[0080] In some embodiments of this application, for tank switching and tank transfer operations, it is necessary to select a suitable alternative tank; for adjusting the load of the equipment, it is also necessary to select a suitable upstream or downstream equipment. Before the operation, this application scores the tanks corresponding to the target tank for each operation, such as tank switching, tank transfer, tank switching, and equipment load adjustment. The score is calculated as: operation probability score * operation convenience score. For ease of description, the target tank that initially needs to be adjusted is denoted as Tank A, and the tank / equipment to be selected during the adjustment operation is denoted as Node B. The scoring function then scores Node B, with the aim of finding a suitable Node B for the adjustment operation of Tank A. Here, operation probability refers to whether there has been a topological connection between Tank A and Node B in the past, representing the actual physical processes of the refinery, such as pipelines and pump sets, which can support such operations. The operational probability score is determined by searching structured and unstructured historical data (such as the refinery's MES system and daily dispatch reports) over a configurable time period to find the number of topological connections between nodes A and B. The operational probability score for node B is calculated as (number of AB topological connections for node B / highest number of AB topological connections among all nodes B) * 10. Node B with the highest number of topological connections receives a maximum operational probability score of 10. Nodes that have never connected receive a score of 0, resulting in a total score of 0. Operational convenience refers to the degree of matching between node B's current adjustable capacity (including remaining tank capacity, available tank capacity, and adjustable unit load) and the amount that needs to be adjusted for tank A. It primarily indicates whether a single operation can resolve tank A's over-limit storage problem. For example, operational convenience scores include 10, 5, and 0 points. A score of 10 indicates that a single operation can complete the tank A storage adjustment; 5 points indicates that multiple operations are required; and 0 points indicates that node B has no further adjustment options.

[0081] The score is calculated using the formula: S = a * b, a = 10c / d, where S is the score of the tank corresponding to the target tank in the current operation; a is the operation probability score; b is the operation convenience score, which is a constant determined based on the following: the number of adjustments required to adjust the excess oil volume of the target tank to no longer exceed the limit using the tank with the current score; c is the number of topological connections from the target tank to the tank with the current score in historical data; and d is the highest number of topological connections among all tanks to be scored in historical data.

[0082] If there is a non-zero score among the oil tanks, the oil tank with the highest score will be used as the working oil tank for the current operation.

[0083] If all tanks have a score of 0, activate the temporary emergency tank to adjust the excess tank inventory of the target tank.

[0084] This application also discloses a refinery production scheduling adjustment system, such as... Figure 4 As shown, it includes:

[0085] The initial module is used to obtain the initial production schedule of the refinery;

[0086] The selection module is used to select target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints.

[0087] The adjustment module is used to adjust the feeding and discharging schemes of each target tank until a refinery production schedule is obtained for target tanks where no oil volume exceeds the upper or lower limit.

[0088] This application also discloses an electronic device, including a memory and a processor, wherein the memory stores a computer program or instructions, and when the computer program or instructions are executed by the processor, they are used to implement at least the above-described method.

[0089] This application also discloses a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, are at least used to implement the above-described method.

[0090] This application also discloses a computer program product stored in a computer-readable storage medium, which, when executed by a processor, is used to implement at least the above-described method.

[0091] Finally, it should be noted that the above description is only a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for adjusting a refinery production scheduling scheme, characterized in that, include: Obtain the initial production schedule from the refinery; Select the target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints; Adjust the feeding and discharging schemes for each target tank until a refinery production schedule is obtained for each target tank where no oil volume exceeds the upper or lower limit.

2. The method for adjusting a refinery production scheduling scheme according to claim 1, characterized in that, The process of obtaining the initial production schedule of the refinery includes: A scheduling model is established based on the refinery's units, tank areas, and material flow. Unit load, scheme selection, and material flow are used as decision variables, while material balance, unit yield, load upper and lower limits, tank capacity upper and lower limits, and scheduling rules are used as constraints. The objective function is to minimize the scheduling operation cost. A mixed integer programming solution is then performed, and the solution is the initial production scheduling scheme for the refinery.

3. The method for adjusting a refinery production scheduling scheme according to claim 1, characterized in that, The adjustment of the feeding and discharging schemes for each of the target tanks includes: The oil volume in the target tank is adjusted by adjusting at least one of the following: The number of upstream devices of the target tank as the oil receiving tank; The output of the upstream device; The number of downstream devices supplied by the target tank; The feed rate of the downstream device; The number of oil tanks receiving oil from the target tank; The number of oil tanks into which oil is poured.

4. The method for adjusting a refinery production scheduling scheme according to claim 3, characterized in that, The adjustment of the feeding and discharging schemes for each of the target tanks includes: The number of upstream devices serving as oil receiving tanks and the number of downstream devices supplying oil to the target tanks are adjusted via a tank-cutting operation. The discharge rate of the upstream device and the feed rate of the downstream device are adjusted by regulating the load operation of the devices. The quantity of oil received from the target tank or the oil poured into the target tank is adjusted by the tank transfer mechanism.

5. The method for adjusting a refinery production scheduling scheme according to claim 4, characterized in that, The adjustment of the feeding and discharging schemes for each of the target tanks includes: Adjust the oil volume in the target tank according to the operational sequence of switching the receiving tank, transferring the oil, switching the auxiliary tank, and adjusting the load of the device.

6. The method for adjusting a refinery production scheduling scheme according to claim 5, characterized in that, The adjustment of the feeding and discharging schemes for each of the target tanks includes: The oil tanks or devices corresponding to each operation, such as switching the receiving oil tank, transferring the oil tank, switching the auxiliary oil tank, and adjusting the load of the device, are scored in sequence. If there is a non-zero score among the scores of the oil tank or device corresponding to the current operation, the oil tank or device with the highest score shall be the preferred object for the current operation. When the scores of the oil tank or device corresponding to the current operation are all 0, a score is given for the oil tank or device corresponding to the next operation. When the score of the oil tank or device corresponding to each operation is 0, the temporary emergency tank is activated to adjust the oil volume of the target tank.

7. The method for adjusting a refinery production scheduling scheme according to claim 6, characterized in that, The formula for calculating the score is: S = a * b a = 10c / d Wherein, S is the score of the oil tank or device corresponding to the target tank in the current operation; a is the operation probability score; b is the operation convenience score, which is a constant determined based on the following: the number of adjustments required to adjust the oil volume of the target tank to no longer exceed the upper or lower limit using the currently rated oil tank or device; c is the number of topological connections from the target tank to the currently rated oil tank or device in historical data; and d is the highest number of topological connections from all oil tanks or devices to be rated to the target tank in historical data.

8. A refinery production scheduling adjustment system, characterized in that, include: The initial module is used to obtain the initial production schedule of the refinery; The selection module is used to select target tanks in the initial production scheduling plan that do not meet the preset tank storage constraints. The adjustment module is used to adjust the feeding and discharging schemes of each target tank until a refinery production schedule is obtained for target tanks with no oil volume exceeding the upper or lower limit.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program or instructions, which, when executed by the processor, are used to implement at least the method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions, which, when executed by a processor, are at least used to implement the method described in any one of claims 1-7.

11. A computer program product, said computer program product being stored in a computer-readable storage medium, characterized in that, When the computer program product is executed by a processor, it is used to implement at least the method described in any one of claims 1-7.

Images