CN108596457B - Method and device for scheduling pipeline transportation - Google Patents
Method and device for scheduling pipeline transportation Download PDFInfo
- Publication number
- CN108596457B CN108596457B CN201810324141.7A CN201810324141A CN108596457B CN 108596457 B CN108596457 B CN 108596457B CN 201810324141 A CN201810324141 A CN 201810324141A CN 108596457 B CN108596457 B CN 108596457B
- Authority
- CN
- China
- Prior art keywords
- transportation
- oil
- pipeline
- batch
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 151
- 230000008569 process Effects 0.000 claims abstract description 81
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 52
- 238000002347 injection Methods 0.000 claims description 41
- 239000007924 injection Substances 0.000 claims description 41
- 238000012360 testing method Methods 0.000 claims description 39
- 238000009826 distribution Methods 0.000 claims description 36
- 239000000243 solution Substances 0.000 claims description 27
- 239000003016 pheromone Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 9
- 238000010998 test method Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 239000003921 oil Substances 0.000 description 233
- 239000000047 product Substances 0.000 description 133
- 230000006870 function Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 10
- 230000001276 controlling effect Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000013439 planning Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 239000002283 diesel fuel Substances 0.000 description 2
- 238000002513 implantation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Pipeline Systems (AREA)
Abstract
The embodiment of the application provides a method and a device for scheduling pipeline transportation, wherein the method comprises the following steps: acquiring a historical scheduling scheme and historical demand data to establish a transport prediction model; determining the time point of each batch of product oil reaching each sub-delivery station in a plurality of batches in the pipeline delivery process through a delivery prediction model; determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of each batch of finished oil in the plurality of batches reaching each sub-transportation station; according to the scheduling scheme, the transportation of the finished oil of each batch in the multiple batches in the transportation process of the finished oil pipeline is controlled, and because the scheme solves the time point of the finished oil of each batch reaching each sub-transportation station by using the transportation prediction model and then determines the specific scheduling scheme according to the sequence of the time points, the technical problems of complex implementation process and low solving efficiency of the existing method are solved.
Description
Technical Field
The application relates to the technical field of oil and gas storage and transportation management, in particular to a scheduling method and device for pipeline transportation.
Background
In the process of oil and gas transportation, a set of transportation pipeline system is usually used for transporting various types of product oil to each sub-transportation station according to a certain sequence, and then the sub-transportation station supplies oil to peripheral areas. Because the oil amount distributed and delivered by any distribution and delivery station along the transportation pipeline affects the distribution of the product oil of the downstream distribution and delivery station, the problem of how to accurately and stably schedule the pipeline transportation process of the product oil is always a concern under the condition of meeting the market demand of the peripheral areas of each distribution and delivery station along the pipeline.
At present, most of the existing methods only solve the MILP (mixed integer programming) model expressed by using continuous time to determine a reasonable scheduling scheme. However, when the above method is implemented, the process is often relatively complex, and the processing efficiency is relatively low. Namely, the method has the technical problems of complex implementation process and low solving efficiency.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a scheduling method and a scheduling device for pipeline transportation, which are used for solving the technical problems of complex implementation process and low solving efficiency of the existing method and achieving the technical effect of quickly and effectively intelligently scheduling the transportation process of a finished oil pipeline.
The embodiment of the application provides a method for scheduling pipeline transportation, which comprises the following steps:
acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil;
training by using the historical scheduling scheme and the historical demand data to establish a transport prediction model;
determining the time point of each batch of product oil reaching each sub-delivery station in a plurality of batches in the pipeline delivery process through the delivery prediction model;
determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of each batch of finished oil in the plurality of batches reaching each sub-transportation station;
and controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme.
In one embodiment, determining, by the transportation prediction model, a time point at which product oil of each of a plurality of batches arrives at each of the distribution stations during transportation of the pipeline includes:
determining an initial solution according to the transportation plan;
and solving the time point of arrival of the product oil of each batch in the plurality of batches at each distribution station by using the transportation prediction model according to the initial solution.
In one embodiment, after determining the scheduling scheme during transportation of the finished oil pipeline, the method further comprises:
checking the scheduling scheme;
under the condition that the scheduling scheme does not meet the preset requirement, correcting the current scheduling scheme according to the following modes:
randomly acquiring a plurality of groups of test schemes according to the current scheduling scheme;
respectively acquiring the path length corresponding to each group of test schemes in the plurality of groups of test schemes and the pheromone concentration corresponding to each group of test schemes in the plurality of groups of test schemes;
and selecting a test scheme meeting the requirements from the plurality of groups of test methods to replace the current scheduling scheme according to the path length corresponding to each group of test schemes in the plurality of groups of test schemes, and updating the pheromone concentration corresponding to the current scheduling scheme by using the pheromone concentration corresponding to the test scheme meeting the requirements.
In one embodiment, determining a dispatch plan during transportation of the product oil pipeline according to a point in time when the product oil of each of the plurality of batches arrives at each of the distribution stations comprises:
and solving by using a mixed integer programming model according to the time point of the product oil of each batch in the plurality of batches reaching each fraction station so as to determine the dispatching scheme.
In one embodiment, the mixed integer programming model is built as follows:
acquiring characteristic parameters of a conveying pipeline;
and determining constraint conditions and an objective function according to the characteristic parameters so as to establish the mixed integer programming model.
In one embodiment, the constraints include at least: injection constraints and pipeline condition constraints.
In one embodiment, the injection constraints include: the injection flow is larger than a first threshold value, wherein the first threshold value is determined according to the relation between the oil mixing section in the transportation pipeline and the Reynolds number.
In one embodiment, the pipe state constraints include: and limiting the occurrence and the stop of the transportation of the pipeline containing the oil mixing section.
The embodiment of the present application further provides a scheduling device for pipeline transportation, including:
the acquisition module is used for acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil;
the establishing module is used for training by utilizing the historical scheduling scheme and the historical demand data to establish a transport prediction model;
the first determining module is used for determining the time point of the finished oil of each batch in the plurality of batches reaching each distribution station in the pipeline transportation process through the transportation prediction model;
the second determining module is used for determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of the finished oil of each batch in the plurality of batches reaching each sub-transmission station;
and the control module is used for controlling the transportation of the finished oil in each batch in the transportation process of the finished oil pipeline according to the scheduling scheme.
In one embodiment, the first determining module comprises:
a first determination unit for determining an initial solution according to the transportation plan;
and the solving unit is used for solving the time point of the finished oil of each batch in the batches reaching each distribution station by using the transportation prediction model according to the initial solution.
In the embodiment of the application, the time points of the finished oil of each batch reaching each sub-transmission station are solved by using the transportation prediction model, and then the specific scheduling scheme is determined according to the sequence of the time points, so that the technical problems of complex implementation process and low solving efficiency of the existing method are solved, and the technical effect of quickly and effectively intelligently scheduling the transportation process of the finished oil pipeline is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a process flow diagram of a method for scheduling pipeline transportation according to an embodiment of the present application;
FIG. 2 is a block diagram of a dispatching device for pipeline transportation according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an electronic device according to a scheduling method for pipeline transportation provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a scenario in which a scheduling method and apparatus for pipeline transportation provided by an embodiment of the present application is applied to determine a scheduling scheme in a product oil transportation process;
FIG. 5 is a schematic diagram of migration of various batches of product oil obtained by applying the scheduling method and apparatus for pipeline transportation provided by the embodiments of the present application in one example scenario;
fig. 6 is a schematic flow diagram of each pipeline in a transport pipeline obtained by applying the scheduling method and apparatus for pipeline transport provided by the embodiment of the present application in a scenario example.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Considering that the existing method usually directly solves the MILP model expressed by continuous time, the solving process is complex. The technical problems of complex implementation process and low solving efficiency often exist in the concrete implementation of the existing method. Aiming at the root cause of the technical problem, the method can utilize historical data (such as a historical scheduling scheme) to solve the time point when the finished oil of each batch reaches each sub-transmission station through a transmission prediction model, and then determine a specific scheduling scheme according to the sequence of the time points, thereby solving the technical problems of complex implementation process and low solving efficiency of the existing method, and achieving the technical effect of quickly and effectively intelligently scheduling the transmission process of the finished oil pipeline.
Based on the thought, the embodiment of the application provides a scheduling method for pipeline transportation. Specifically, please refer to a processing flow chart of a scheduling method for pipeline transportation according to an embodiment of the present application shown in fig. 1. The method for scheduling pipeline transportation provided by the embodiment of the application can comprise the following steps in specific implementation.
S11: acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: and the demand quantity and the demand time of each delivery station for each batch of product oil.
In this embodiment, the historical scheduling scheme may be specifically understood as a finished oil transportation planning control scheme in the history of the transportation pipeline, and the control scheme may specifically include: historically, the time and amount of each batch of product oil injected at the first station of the transport pipeline, and the time and amount of each batch of product oil separately delivered and downloaded at each delivery station along the transport pipeline.
In the present embodiment, the historical demand data may be specifically understood as demand amount, demand time, and the like of different types or batches of product oil at each delivery station along the delivery pipeline.
In this embodiment, the historical scheduling plan, the historical demand data, and the like may be used as sample data for establishing the transportation prediction model. Of course, the sample data listed is only an illustrative example, and should not be construed as limiting the embodiments of the present application. In specific implementation, according to specific situations and precision requirements, other data except the historical scheduling scheme and the historical demand data can be acquired as sample data for training and learning. For example, historical transportation cost data and the like may also be obtained.
S12: and training by using the historical scheduling scheme and the historical demand data to establish a transport prediction model.
In this embodiment, the scheduling scheme to be determined in this application may be specifically understood as a schedule for the current or future production oil transportation, and the scheme may specifically include: the time and the quantity of the product oil of each batch injected at the first station of the transportation pipeline at present or in the future, and the time and the quantity of the product oil of each batch respectively transported and downloaded at each transportation station along the transportation pipeline. Therefore, in the process of conveying the product oil, the product oil can be conveyed economically and effectively according to the scheduling plan on the premise of meeting the product oil requirements of each sub-conveying station, the conveying cost is reduced, and the product oil waste in the conveying process is reduced.
In one embodiment, when a scheduling scheme in a specific finished oil pipeline transportation process is solved, because the demand and the download of different batches of finished oil at each time point along each distribution station on a finished oil transportation pipeline can affect the scheduling of the whole finished oil pipeline transportation, the data to be analyzed and solved is huge. When the existing method is used for analyzing and solving the data, due to the limitation of the method, the efficiency is lower and the accuracy is not high, so that the process of solving the scheduling scheme based on the existing method is complex and the efficiency is low. Due to the above problems in the implementation of the existing methods, the present embodiment proposes a method for quickly and effectively solving the above complex problems: firstly, determining time points of each sub-transmission station of each batch in a plurality of batches in the pipeline transmission process by using a neural network model as a transmission prediction model, and using the time points as time constraint variables; with the time constraint variables known, a planning model for product oil transport, i.e., a mixed integer planning model, is solved to quickly solve for a relatively high accuracy scheduling plan.
In the present embodiment, the transportation prediction model may be understood as a learning model based on a neural network. The Neural Networks (NN) may be a complex network system formed by widely connecting a large number of simple processing units (called neurons), which can simulate many basic features in human brain functions, become a highly complex nonlinear dynamical learning system, have the characteristics of massive parallelism, distributed storage and processing, self-organization, self-adaptation and self-learning capabilities, and the like, and are suitable for processing inaccurate and fuzzy information processing problems which need to consider many factors and conditions at the same time.
In one embodiment, the transportation prediction model may be specifically considered as a model established in advance based on a historical scheduling scheme and historical demand data. However, because the model is established based on the neural network, when the model is used for analyzing and processing the current finished oil transportation process, the model can also analyze and learn the related data in the current finished oil transportation process so as to continuously enrich the database of the model, automatically improve and update the model in real time, adapt to the new finished oil transportation process in time and further improve the precision of the model.
S13: and determining the time point of each batch of the product oil in the plurality of batches in the pipeline transportation process to reach each distribution station through the transportation prediction model.
In one embodiment, considering the real product oil transportation process, different distribution and transportation stations are required to distribute and download a plurality of different types of product oil to meet the market demand of the area where the distribution and transportation station is located. In view of transportation costs, the same set of transportation pipelines is typically used to transport a plurality of different types of product oil. Furthermore, the product oil of different types is simultaneously transported in the transportation pipeline, so that the product oil is easy to mix to form a longer oil mixing section, and the product oil is wasted. Therefore, in order to avoid oil mixing as much as possible, the same conveying pipeline is usually used to convey multiple different types of conveyed product oil in batches. For example, when transporting specifically, oil 93 can be transported as a first batch of product oil, and then oil 97 can be transported as a second batch of product oil.
In the present embodiment, the two adjacent batches of product oil may specifically refer to different types of product oil. For example, a first batch of product oil is 97 # oil and a second batch of product oil immediately following the first batch of product oil may be 93 # oil. Product oils that are not adjacent batches may be different types of product oils or the same type of product oils. For example, the third batch of finished oil next to the second batch of finished oil may be 97 # oil, or may be another type of finished oil other than 93 # oil.
In an embodiment, the determining, by the transportation prediction model, a time point when the product oil of each of the plurality of batches reaches each of the distribution stations in the pipeline transportation process may include the following steps:
s1: an initial solution is determined from the transportation plan.
S2: and solving the time point of arrival of the product oil of each batch in the plurality of batches at each distribution station by using the transportation prediction model according to the initial solution.
In one embodiment, the transportation plan may be specifically determined according to a historical scheduling scheme and historical demand data. In specific implementation, the current or future downloading plan of each distribution station for each batch of product oil can be predicted to serve as the transportation plan according to a historical scheduling scheme and historical demand data and by combining the current market demand.
In an embodiment, the determining an initial solution according to the transportation plan may include: and inputting the transport plan as an input into the established transport prediction model to obtain a corresponding solution, namely the initial solution.
In an embodiment, the solving, according to the initial solution, a time point when the product oil of each of the plurality of batches reaches each of the distribution stations by using the transportation prediction model may include: and carrying out repeated iterative solution on the initial solution agent transportation prediction model to obtain a converged solution, namely solving to obtain the time point of the finished oil of each batch in the batches reaching each sub-transportation station.
In one embodiment, the time point of arrival of the product oil of each of the plurality of solved batches at each of the distribution stations may be specifically understood as an optimal time point sequence; the time point at which the product oil of each of the plurality of batches arrives at each of the delivery stations is determined, and the time constraint variable in the dispatch plan can be considered to be determined.
S14: and determining a scheduling scheme in the transportation process of the product oil pipeline according to the time point of each batch of product oil in the plurality of batches reaching each distribution station.
In one embodiment, after determining the time point when the product oil of each of the plurality of batches reaches each of the distribution stations (i.e., the time point sequence is known), the determination problem of the original scheduling scheme can be reduced to a scheduling optimization problem about the flow constraint variable on the premise that the time constraint variable is known.
In an embodiment, the determining a scheduling scheme during transportation of the product oil pipeline according to the time point of arrival of the product oil of each of the plurality of batches at each of the distribution stations may include: and solving by using a mixed integer programming model (namely an MILP model) according to the time point of the finished oil of each batch in the plurality of batches reaching each fraction station so as to determine the most appropriate programming scheme as the dispatching scheme.
In one embodiment, in order to establish a mixed integer programming model with relatively high precision, in a specific implementation, the mixed integer programming model may be established as follows:
s1: and acquiring characteristic parameters of the conveying pipeline.
S2: and determining constraint conditions and an objective function according to the characteristic parameters so as to establish the mixed integer programming model.
In an embodiment, the characteristic parameters of the transportation pipeline may specifically include: length of the transport pipe, wall thickness of the transport pipe, inner diameter of the transport pipe, and the like. Of course, in addition to the above listed characteristic parameters, in specific implementation, other parameters of the transportation pipeline may be obtained as the characteristic parameters of the transportation pipeline. The present application is not limited thereto.
In one embodiment, the above-mentioned obtaining and utilizing of the characteristic parameters of the transport pipeline is only an illustrative description. And should not be construed as limiting the embodiments of the present application. In specific implementation, other related data can be acquired according to specific situations and construction requirements to establish the mixed integer programming model. For example, the mixed integer programming model can be established by acquiring the running expense data of a pump in a conveying pipeline, the conveying cost data of unit product oil and the like in combination with the characteristic parameters of the conveying pipeline.
In one embodiment, in a specific implementation, a minimum value of a deviation value between an actual download amount of each substation and a predicted demand amount of each substation may be obtained as the objective function. In specific implementation, the objective function may be established as follows:
wherein, CBIn particular, the cost of the economic loss, CNY/m, caused by the download bias3,CBPIn particular, the cost of the economic loss caused by multiple downloads, CNY/m3,CBNIn particular, the cost of the economic loss caused by the low download, CNY/m3,VXi,oCan be specifically expressed as the actual download amount, m, of the oil product at the ith station o3, VSi,oCan be specifically expressed as the demanded quantity of oil product at the ith station o, m3,ρoMay particularly be expressed asDensity of o oil product kg/m3Specifically, io may be represented as a station yard and an oil product number, specifically, I may be represented as a station yard number set, and specifically, O may be represented as an oil product number set.
In one embodiment, the objective function may be further linearized to facilitate subsequent solution. Specifically, the linearization process may be performed as follows:
VXi,o-VSi,o+EAi,o≥0,i∈I,o∈O
VXi,o-VSi,o+EBi,o≥0,i∈I,o∈O
wherein E isAi,oIn particular, it can be expressed as the volume of oil at station i o that is less than the required amount of oil, m3,EBi,oIn particular, it can be expressed as the volume of oil at station i o which is more loaded than the demanded quantity, m3。
In one embodiment, the constraints may include at least: injection constraints and pipeline state constraints, etc. Of course, the above two constraints are only listed for better illustration of the embodiments of the present application. In specific implementation, other types of constraints can be introduced as constraints in the mixed integer programming model according to specific situations and precision requirements. Specifically, one or more of the following listed constraints may be established as constraints of the mixed integer programming model in combination with the injection constraints and the pipe state constraints: download constraints, time constraints, and the like. The specific form and number of other types of constraints introduced are not a limitation of the present application.
In one embodiment, it is contemplated that existing methods will determine the corresponding injection constraints based mostly on a lower limit of the plant flow. The lower limit value of the flow of the equipment is also called a lower limit of the pipeline conveying flow, and the value can be determined according to the conveying flow limit of an oil conveying pump in a conveying pipeline, the range limit of metering equipment and the operation limit of other equipment. In the normal transportation process, when the transportation of the product oil is stopped, the injection flow rate at the start of transportation needs to be larger than the lower limit value of the flow rate of the equipment. However, in practice, it has been found that as the reynolds number (a dimensionless number that can be used to characterize fluid flow) increases during actual transport, the amount of oil mixing in the pipeline also decreases, and when the reynolds number is greater than a critical value, the amount of oil mixing becomes relatively small. Therefore, when the same set of transportation pipeline is utilized to transport multiple batches of product oil, an oil mixing interface (oil mixing section) inevitably appears in the pipeline, and in order to reduce the oil mixing amount in the transportation process and reduce the loss of the product oil caused by oil mixing, the injection flow can be increased to ensure that the Reynolds number is greater than a certain critical value, so that the oil mixing amount is relatively small. Based on the above, the injection constraint may specifically include: the injection flow rate is greater than a first threshold, wherein the first threshold can be specifically determined according to the relation between the oil mixing section in the transportation pipeline and the Reynolds number.
In one embodiment, in addition to setting the injection constraints as described above, further detailed and refined injection constraints can be established with reference to the following equations:
VJk≤(τk+1-τk)QJmax,k∈K
VJk≥(τk+1-τk)QJmax,k∈K
wherein, VJkIt can be expressed in particular as the initial injection volume, Q, in the transport pipeJmaxIt can be expressed in particular as the maximum injection flow, m3/h,QJminIt can be expressed in particular as the minimum injection flow, m3/h,τkSpecifically, the length of the kth time window may be expressed, h, K may be specifically expressed as a time window number, and K may be specifically expressed as a time window number set.
According to the above equation, considering that the cumulative injection amount of the head station is equal to the cumulative injection amount of the head station at the starting time of the previous time window plus the injection amount of the head station in the previous time window, it can be obtained:
VJTk=VJTk-1+VJk-1,k∈K
wherein, VJTkIn particular, m may be expressed as the cumulative injection amount at the start of the kth time window3,,VJTk-1It can be expressed specifically as the cumulative injection quantity, m, at the beginning of the k-1 time window3,VJk-1It can be expressed as the implantation amount m in the k-1 time window3。
According to the injection constraint conditions, in combination with the volume coordinate definition of the new batch of product oil, the volume coordinate of the new batch of product oil may be equal to the negative value of the initial injection volume between the starting time of the transportation process and the starting time of injecting the batch, and may specifically be expressed by the following equation:
VZTj≤-VJTk+(1-FTJk,j)M,j∈Jnew,k∈K
VZTj≥-VJTk+(FTJk,j-1)M,j∈Jnew,k∈K
wherein, FTJk,jIt can be expressed as an injection binary variable, if the injection of the jth batch is started at the beginning of the kth time window, F TJk,j1, otherwise FTJk,j=0,VZTjCan be expressed as the volume coordinate of the oil head of the jth batch, m3M may specifically be represented as a maximum.
Further, at each time node, the inventory of the first batch of oil tanks can be calculated and tracked. In specific implementation, the method can be realized according to the following formula:
wherein, VINVo,kWhich can be expressed in particular as the start of the first kth time window o stock of oil tanks, m3, VJkIn particular, m can be expressed as the implantation amount in the k time window3,QPoCan be expressed as the unit production m of the oil tank3/h,FTJDk,jIt can be specifically expressed as an injection state binary variable, if the beginning time of the kth time window is injecting the jth batch, then F TJDk,j1, otherwise FTJDk,j=0,BJOj,oCan be specifically expressed as a batch type binary parameter, if the jth batch is o oil product, B JOj,o1, otherwise BJOj,o=0。
In summary, there is a constraint on the tank inventory of the various product oils at the head station, that is, the following constraint conditions exist for the tank inventory of the various product oils at the head station:
VINVmaxo≥VINVo,k≥VINVmino,k∈K,o∈O
wherein, VINVmaxoIt can be expressed in particular as the maximum stock of the oil product at the first stop o, m3,VINVminoCan be expressed in particular as the minimum stock of oil products at the first stop o, m3。
In one embodiment, it is fully considered that during the transportation of multiple batches of product oil by using the transportation pipeline, a mixed oil boundary or mixed oil section is formed between different batches of product oil, in this case, if the transportation is stopped suddenly, the different batches of product oil are mixed at the boundary position obviously, and the mixed oil amount is increased. This phenomenon is more pronounced especially in areas with large elevation differences. For example, if the product oil in the No. 3 pipeline stops suddenly, the product oil in the higher batch is mixed into the product oil in the lower batch more obviously due to the gravity, and the mixed oil amount is increased. In view of the above, the present embodiment proposes to set a pipe constraint condition. Wherein, the above-mentioned pipe constraint condition may specifically include: and limiting the occurrence and the stop of the transportation of the pipeline containing the oil mixing section. The above pipeline constraints are understood to reduce as little as possible the probability of a shut-down of a pipeline containing a mixed oil fraction.
In one embodiment, in combination with the above-mentioned idea, when implementing specifically, the specific pipe state constraint condition may be established in the following manner, so as to avoid the transportation stop operation as much as possible when the oil mixing section exists in the pipe:
1-FMi,k≥BISi,k,k∈K,i∈I
wherein, Voi′,kSpecifically, it can be expressed as the download amount, m, of the ith station in the kth time window3,QPLmaxiIt can be expressed in particular as the maximum flow, m, of the ith pipe section3/h,QPLMminiIt can be expressed as the minimum flow rate when the ith pipe section is not mixed with oil, m3/h,QPLNminiIn particular, m can be expressed as the minimum flow rate of the i-th pipe section in the presence of the oil mixture3/h,FMi,kCan be specifically expressed as a stop-delivery binary variable, if the ith pipe section stops delivering F in the kth time window Mi,k0, otherwise FMi,k=1,BISi,kSpecifically, the mixing oil can be expressed as a binary variable of mixing oil, if mixing oil exists in the ith pipe section in the kth time window and the conveying cannot be stopped, B ISi,k1, otherwise BISi,k=0。
Considering also that when the pipeline stops delivering, the flow in the pipeline can become 0, and the following can be obtained:
further, according to volume conservation, the volume coordinate of the number i of the delivery station minus the volume coordinate of the number j of the batches should be equal to the sum of the total volume injected by the first station before the time when the number j of the batches reaches the number i of the delivery station minus the volume downloaded by each delivery station before the number i of the delivery station in the time period from the time when the number j of the batches of the product oil reaches the number i of the delivery station to the time when the number j of the batches reaches each delivery station:
wherein, VZSiWhich may be specifically expressed as the volume coordinate of the ith station, m3, VZJjCan be specifically expressed as the volume coordinate of the oil head of the jth batch, m3, FKARBk,i,jSpecifically, the method can be expressed as a time node ordering binary parameter, and if the kth time window is earlier than the time of the jth batch of oil heads reaching the ith station, F KARBk,i,j1, otherwise FKARBk,i,j=0,FKARBk,i,jAnd FKARBk,i′,jData corresponding to different transmission distribution stations.
In one embodiment, when implemented, the download constraints may be set as follows:
if the sub-delivery station does not download the product oil, the download volume of the sub-delivery station under the time window can be set as 0:
VOi,k≤BTOi,kM,k∈K,i∈I
wherein, BTOi,kSpecifically, the information can be expressed as a download state binary variable, and if the ith station does not download the oil in the kth time window, B TOi,k1, otherwise BTOi,k=0。
Due to the limitation of the receiving capability of the metering equipment and each sub-transmission station, the download volume of each sub-transmission station needs to meet the following constraint conditions:
VOi,k≤(τk+1-τk)QOmaxi+(1-BTOi,k)M,k∈K,i∈I
VOi,k≥(τk+1-τk)QOmini+(BTOi,k-1)M,k∈K,i∈I
wherein Q isOmaxiWhich may be specifically expressed as the maximum download traffic, m, of the ith station3/h,QOminiWhich may be specifically expressed as the minimum download traffic, m, of the ith station3/h,BTOi,kSpecifically, the information can be expressed as a download state binary variable, and if the ith station does not download the oil in the kth time window, B TOi,k1, otherwise BTOi,k=0。
Under the premise that the time point of each batch of the product oil in the plurality of batches reaching each distribution station is known, which batch of the product oil is downloaded by each distribution station in each time window can be known, and the actual volume downloaded by each distribution station in the corresponding time window can be further determined. When a batch is determined to be delivering a certain type of product oil, the amount of download of the dispensing station at the batch should be equal to the amount of download of the batch, and when a batch is delivering the certain type of product oil, the dispensing station cannot obtain the certain type of product oil from the batch. According to the above idea, the download constraint condition can be established as follows:
wherein, VOi,kSpecifically, it can be expressed as the download amount, m, of the ith station in the kth time window3,FTDi,k,jSpecifically, the parameter can be expressed as a binary parameter for oil product download, and if the ith station is downloading the jth batch in the kth time window, F TDi,k,j1, otherwise FTDi,k,j=0,BJOj,oCan be specifically expressed as a batch type binary parameter, if the jth batch is o oil product, B JOj,o1, otherwise BJOj,o=0。,VSi,oCan be specifically expressed as the demanded quantity of oil product at the ith station o, m3。
In one embodiment, consideration is given to the specific product oil transportation processIn this case, there is a time constraint condition, specifically, the time after the time node is sorted is certainly later than the time before the time node is sorted. According to the above idea, the time constraint condition can be established as follows: tau isk+1≥τk,k∈K。
And establishing a corresponding objective function and constraint conditions to obtain the mixed integer programming model. In the case where the point in time at which the product oil of each of the plurality of batches arrives at each of the distribution stations is known (i.e., the time constraint variable is known), the above-described mixed integer programming model may further simplify understanding of the programming model with respect to the flow constraint variable. Because the time constraint variable is not considered any more, the difficulty of solving the mixed integer programming model is greatly reduced, and the implementation efficiency of subsequently solving the model to obtain the final scheduling scheme can be effectively improved.
S15: and controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme.
In this embodiment, after the scheduling scheme is obtained by solving, the injection time and the injection amount of each batch of product oil in the plurality of batches of product oil at the head station can be accurately controlled according to the scheduling scheme; at each distribution station, the download time and download amount of each of the plurality of batches of product oil; and the conveying of the product oil in each pipeline in the conveying pipeline is started and stopped, so that the conveying of the product oil in each batch in a plurality of batches in the conveying process of the product oil pipeline can be accurately and effectively controlled.
In the embodiment of the application, compared with the existing method, the time points of the finished oil of each batch reaching each sub-transmission station are solved by using the transportation prediction model, and the specific scheduling scheme is determined according to the sequence of the time points, so that the technical problems of complex implementation process and low solving efficiency of the existing method are solved, and the technical effect of quickly and effectively intelligently scheduling the transportation process of the finished oil pipeline is achieved.
In one embodiment, in order to further improve the accuracy of the determined scheduling scheme and reduce errors, in particular, after determining the scheduling scheme in the transportation process of the finished oil pipeline, the method may further include the following steps:
s1: checking the scheduling scheme;
s2: under the condition that the scheduling scheme does not meet the preset requirement, correcting the current scheduling scheme according to the following modes:
s2.1: randomly acquiring a plurality of groups of test schemes according to the current scheduling scheme;
s2.2: respectively acquiring the path length corresponding to each group of test schemes in the plurality of groups of test schemes and the pheromone concentration corresponding to each group of test schemes in the plurality of groups of test schemes;
s2.3: and selecting a test scheme meeting the requirements from the plurality of groups of test methods to replace the current scheduling scheme according to the path length corresponding to each group of test schemes in the plurality of groups of test schemes, and updating the pheromone concentration corresponding to the current scheduling scheme by using the pheromone concentration corresponding to the test scheme meeting the requirements.
According to the method, the test scheme with the shortest path length can be screened from the plurality of test schemes to be used as the test scheme meeting the requirement to replace the current scheduling scheme, so that the scheduling scheme is corrected, and the accuracy of the scheduling scheme is improved.
In this embodiment, after correcting the time point when the product oil of each of the multiple batches reaches each of the sub-delivery stations, the determining the scheduling scheme in the transportation process of the product oil pipeline according to the time point when the product oil of each of the multiple batches reaches each of the sub-delivery stations may include: and determining a scheduling scheme in the transportation process of the finished oil pipeline and determining the scheduling scheme in the transportation process of the finished oil pipeline according to the corrected time point of the finished oil in each batch in the plurality of batches reaching each sub-transmission station.
In one embodiment, it is further necessary to supplement that, after the scheduling scheme is corrected, the corrected scheduling scheme may be checked again. If the corrected scheduling scheme can not meet the preset requirement, the corrected scheduling scheme can be subjected to one or more times of iterative correction according to the mode and the pheromone concentration corresponding to the corrected scheduling scheme until the scheduling scheme meeting the preset requirement is obtained. The preset requirement can be specifically determined according to specific construction precision. The present application is not limited thereto.
In one embodiment, it should be noted that, as a model with self-learning capability, such as a transport prediction model, is mainly used, and a corresponding interactive algorithm is combined, the transport prediction model used in the process of determining the scheduling scheme by using the method for multiple times can be continuously learned to grow, and then the subsequent transport prediction model based on the continuous learning to grow can more accurately and quickly determine the corresponding scheduling scheme.
From the above description, it can be seen that the pipeline transportation scheduling method provided in the embodiment of the present application solves the time point when the finished oil of each batch reaches each sub-transportation station by using the transportation prediction model, and determines the specific scheduling scheme according to the sequence of the time points, thereby solving the technical problems of complex implementation process and low solution efficiency of the existing method, and achieving the technical effect of performing fast and effective intelligent scheduling on the finished oil pipeline transportation process; and the influence of the mixed oil quantity is considered, and an injection constraint condition and a pipeline state constraint condition are introduced, so that the error of the established mixed integer programming model can be reduced, and a more accurate scheduling scheme is obtained.
Based on the same inventive concept, the embodiment of the present invention further provides a scheduling device for pipeline transportation, as described in the following embodiments. Because the principle of solving the problems of the scheduling device for pipeline transportation is similar to the scheduling method for pipeline transportation, the implementation of the scheduling device for pipeline transportation can refer to the implementation of the scheduling method for pipeline transportation, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Please refer to fig. 2, which is a structural diagram of a scheduling apparatus for pipeline transportation according to an embodiment of the present application, where the apparatus may specifically include: the system comprises an obtaining module 21, an establishing module 22, a first determining module 23, a second determining module 24, and a control module 25, and the structure will be described in detail below.
The obtaining module 21 may be specifically configured to obtain a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil;
the establishing module 22 may be specifically configured to perform training by using the historical scheduling scheme and the historical demand data to establish a transportation prediction model;
the first determining module 23 may be specifically configured to determine, through the transportation prediction model, a time point at which the product oil of each of the multiple batches reaches each of the sub-transportation stations in the pipeline transportation process;
the second determining module 24 may be specifically configured to determine a scheduling scheme in the transportation process of the product oil pipeline according to a time point when the product oil of each of the multiple batches reaches each of the distribution stations;
the control module 25 may be specifically configured to control transportation of each batch of the product oil in the plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme.
In one embodiment, in order to determine, by the transportation prediction model, a time point when the product oil of each of the plurality of batches reaches each of the distribution stations in the pipeline transportation process, the first determination module 21 may specifically include the following structural units:
the first determining unit can be specifically used for determining an initial solution according to the transportation plan;
and the solving unit can be specifically used for solving the time point of arrival of the product oil of each batch in the batches at each sub-delivery station by using the transportation prediction model according to the initial solution.
In an embodiment, in order to ensure that the determined scheduling scheme is reasonable and accurate, the apparatus may further include a correction module, where the correction module may be specifically configured to check the scheduling scheme; under the condition that the scheduling scheme does not meet the preset requirement, correcting the current scheduling scheme according to the following modes: randomly acquiring a plurality of groups of test schemes according to the current scheduling scheme; respectively acquiring the path length corresponding to each group of test schemes in the plurality of groups of test schemes and the pheromone concentration corresponding to each group of test schemes in the plurality of groups of test schemes; and selecting a test scheme meeting the requirements from the plurality of groups of test methods to replace the current scheduling scheme according to the path length corresponding to each group of test schemes in the plurality of groups of test schemes, and updating the pheromone concentration corresponding to the current scheduling scheme by using the pheromone concentration corresponding to the test scheme meeting the requirements.
In one embodiment, in order to determine the scheduling scheme during transportation of the product oil pipeline according to the time point of arrival of the product oil of each of the plurality of batches at each of the distribution stations, the second determining module 22 may be implemented according to the following procedures: and solving by using a mixed integer programming model according to the time point of the product oil of each batch in the plurality of batches reaching each fraction station so as to determine the dispatching scheme.
In an embodiment, when implemented, the second determining module 22 may establish the mixed integer programming model according to the following procedure: acquiring characteristic parameters of a conveying pipeline; and determining constraint conditions and an objective function according to the characteristic parameters so as to establish the mixed integer programming model.
In one embodiment, the constraints include at least: injection constraints and pipeline state constraints, etc. Of course, the above-mentioned constraints are only for better explanation of the embodiments of the present application. In specific implementation, other types of constraint conditions can be introduced as the constraint conditions according to specific situations and construction requirements. The present application is not limited thereto.
In one embodiment, the injection constraint may specifically include: the injection flow is larger than a first threshold value, wherein the first threshold value is determined according to the relation between the oil mixing section in the transportation pipeline and the Reynolds number.
In one embodiment, the pipe state constraint may specifically include: and limiting the occurrence and the stop of the transportation of the pipeline containing the oil mixing section.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should be noted that, the systems, devices, modules or units described in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, in the present specification, the above devices are described as being divided into various units by functions, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
Moreover, in the subject specification, adjectives such as first and second may only be used to distinguish one element or action from another element or action without necessarily requiring or implying any actual such relationship or order. References to an element or component or step (etc.) should not be construed as limited to only one of the element, component, or step, but rather to one or more of the element, component, or step, etc., where the context permits.
From the above description, it can be seen that the pipeline transportation scheduling device provided in the embodiment of the present application solves the time point when the finished oil of each batch reaches each sub-transportation station by using the transportation prediction model, and determines the specific scheduling scheme according to the sequence of the time points, thereby solving the technical problems of complex implementation process and low solution efficiency of the existing method, and achieving the technical effect of performing fast and effective intelligent scheduling on the finished oil pipeline transportation process; and the influence of the mixed oil quantity is considered, and an injection constraint condition and a pipeline state constraint condition are introduced, so that the error of the established mixed integer programming model can be reduced, and a more accurate scheduling scheme is obtained.
The embodiment of the present application further provides an electronic device, which may specifically refer to a schematic structural diagram of the electronic device shown in fig. 3 and based on the scheduling method for pipeline transportation provided in the embodiment of the present application, where the electronic device may specifically include an input device 31, a processor 32, and a memory 33. The input device 31 may be specifically configured to input a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: and the demand quantity and the demand time of each delivery station for each batch of product oil. The processor 32 may be specifically configured to perform training using the historical scheduling scheme and the historical demand data to establish a transportation prediction model; determining the time point of each batch of product oil reaching each sub-delivery station in a plurality of batches in the pipeline delivery process through the delivery prediction model; determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of each batch of finished oil in the plurality of batches reaching each sub-transportation station; and controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme. The memory 33 may specifically be used to store the incoming historical scheduling scheme, historical demand data, and intermediate data generated by the processor 32.
In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and a program for processing the data into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.
In this embodiment, the functions and effects specifically realized by the electronic device can be explained by comparing with other embodiments, and are not described herein again.
The present application further provides a computer storage medium of a scheduling method based on pipeline transportation, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements: acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil; training by using the historical scheduling scheme and the historical demand data to establish a transport prediction model; determining the time point of each batch of product oil reaching each sub-delivery station in a plurality of batches in the pipeline delivery process through the delivery prediction model; determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of each batch of finished oil in the plurality of batches reaching each sub-transportation station; and controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme.
In the present embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.
In a specific implementation scenario example, the scheduling method and device for providing pipeline transportation according to the embodiment of the present application are applied to perform specific scheduling control on the finished oil pipeline transportation in the Hunan region. The following can be referred to as a specific implementation process.
And selecting an actual pipeline in the Hunan area as a finished oil conveying pipeline to be regulated and controlled for analysis so as to determine a scheduling scheme in the finished oil conveying process based on the conveying pipeline. And acquiring relevant data of the pipeline, and knowing that: the total length of the pipeline IS 540.7km, the starting point IS an IS oil refinery, the terminal point IS to a No. 6 oil depot, 5 stations are arranged along the pipeline in total, and 17 manual emergency cut-off valves are arranged. The pipeline operation management and control adopts an SCADA system to carry out remote monitoring and data acquisition management, and the whole line carries out control and management according to three levels of central control, station control and local control of the authority. Referring to fig. 4, related contents shown in a scene schematic diagram of a scheduling scheme in a product oil transportation process are determined by applying the scheduling method and apparatus for pipeline transportation provided by an embodiment of the present application in a scene example. Wherein, this pipeline full line closed transport: 0# common diesel oil, 0# automotive diesel oil, 92# gasoline and 95# gasoline (four different types of finished oil). When the oil product conveying sequence is determined, an optimal sequencing scheme is determined according to the oil product quality condition in the actual operation process according to the principle that oil products with similar properties are adjacently arranged, and the batch conveying sequence is 0# diesel (first batch of finished oil), 0# common diesel (second batch of finished oil), 0# diesel (third batch of finished oil), 92# gasoline (fifth batch of finished oil), 95# gasoline (sixth batch of finished oil), 92# gasoline (seventh batch of finished oil), and 0# diesel (eighth batch of finished oil). The design pressure, pipe diameter, wall thickness, spacing and pipe volume (i.e. the characteristic parameters of the transport pipeline) of each pipe section in the transport pipeline can be referred to the main parameters of the pipeline system shown in table 1. The flow range of each pipe section in the conveying pipeline can be obtained, and the table of the flow range of the pipe sections shown in the table 2 can be referred to. Wherein, i # S-j # S represents a pipe section between the station I and the station J in the transportation pipeline. For example, 1# S-2 # S may represent a pipe segment between station 1 and station 2, with IS representing the lead station.
TABLE 1 Main parameters of the pipe system
TABLE 2 pipe segment flow range chart
At the initial moment, the pipeline is completely filled with the No. 0 diesel, and the oil batch and the planned delivery amount required to be delivered in the dispatching cycle and the demand (i.e. the delivery plan) of each station (i.e. the branch delivery station) can refer to the first station injection plan shown in the table 3 and the demand plan table of each station shown in the table 4.
Table 3 first injection schedule
TABLE 4 requirements plan table for each station
And according to the data, determining the time point (obtaining a time constraint variable) when the product oil of each batch in the multiple batches reaches each sub-delivery station in the pipeline delivery process by pre-establishing a delivery prediction model. Specifically, fig. 5 is a schematic diagram of migration of each batch of product oil obtained by applying the scheduling method and apparatus for pipeline transportation according to the embodiment of the present application in one scenario example. In the figure, i # S-j # S represents a pipe section between the station i and the station j in the transport pipeline. For example, 1# S-2 # S may represent a pipe segment between station 1 and station 2, with IS representing the lead station. In the figure, the abscissa represents time (unit: h) and the ordinate represents length (unit: km).
Under the condition that the time points of the product oil of each batch in the multiple batches reaching each distribution station are known, planning and solving are carried out by using a pre-established mixed integer planning model, and flow constraint variables of each pipe section are obtained (the complete dispatching scheme is obtained by combining the previous time constraint variables). Specifically, a schematic flow diagram of each pipeline in the transportation pipeline obtained by applying the scheduling method and apparatus for pipeline transportation provided by the embodiment of the present application in a scenario example shown in fig. 6 may be referred to. The Flow rate is specifically used for representing the Flow rate of the product oil in the conveying pipeline, the Upper limit is specifically used for representing the Upper Flow limit, and the Lower limit is used for representing the Lower Flow limit.
And then controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme, so as to accurately and effectively regulate and control the product oil transportation process of the whole transportation pipeline.
According to the scene example, the pipeline transportation scheduling method and device provided by the embodiment of the application are verified, the time points of the finished oil of each batch reaching each sub-transportation station are solved by using the transportation prediction model, and the specific scheduling scheme is determined according to the sequence of the time points, so that the technical problems of complex implementation process and low solving efficiency in the existing method are solved, and the technical effect of quickly and effectively intelligently scheduling the finished oil pipeline transportation process is achieved.
Although various specific embodiments are mentioned in the disclosure of the present application, the present application is not limited to the cases described in the industry standards or the examples, and the like, and some industry standards or the embodiments slightly modified based on the implementation described in the custom manner or the examples can also achieve the same, equivalent or similar, or the expected implementation effects after the modifications. Embodiments employing such modified or transformed data acquisition, processing, output, determination, etc., may still fall within the scope of alternative embodiments of the present application.
Although the present application provides method steps as described in an embodiment or flowchart, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded.
The devices or modules and the like explained in the above embodiments may be specifically implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the present application, the functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules, and the like. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and other divisions may be realized in practice, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, or the like, and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device) to execute the method according to the embodiments or some parts of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
While the present application has been described by way of examples, those of ordinary skill in the art will appreciate that there are numerous variations and permutations of the present application that do not depart from the spirit of the present application and that the appended embodiments are intended to include such variations and permutations without departing from the present application.
Claims (7)
1. A scheduling method for pipeline transportation is characterized by comprising the following steps:
acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil;
training by using the historical scheduling scheme and the historical demand data to establish a transport prediction model;
determining the time point of each batch of product oil reaching each sub-delivery station in a plurality of batches in the pipeline delivery process through the delivery prediction model;
determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of each batch of finished oil in the plurality of batches reaching each sub-transportation station;
controlling the transportation of each batch of product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme;
the time points of the finished oil of each batch in the multiple batches reaching each sub-delivery station in the pipeline transportation process determined by the transportation prediction model comprise the optimal time point sequence, and the time points of the finished oil of each batch in the multiple batches reaching each sub-delivery station are used for determining time constraint variables in the dispatching scheme;
wherein the constraint conditions at least comprise: injection constraints and pipeline state constraints; the injection constraints include: the injection flow is larger than a first threshold value, and the first threshold value is determined according to the relation between an oil mixing section in the transportation pipeline and the Reynolds number; the pipe state constraints include: limiting the occurrence and the stop of the transportation of the pipeline containing the oil mixing section;
the pipeline state constraint condition is specifically constructed according to the following formula:
wherein,for the first injection volume in the transport pipe,the amount of downloading of the ith station in the kth time window,the maximum flow rate of the ith pipe segment,the minimum flow rate when the ith pipe section is not mixed with oil,is the minimum flow rate when the oil mixture exists in the ith pipe section,is a binary variable for stopping conveying, if the ith pipe section stops conveying in the kth time windowOtherwise;Is a binary variable of mixed oil, if mixed oil exists in the ith pipe section in the kth time window and can not stop conveying,otherwise。
2. The method of claim 1, wherein determining, via the transport prediction model, a point in time at which product oil from each of a plurality of batches arrives at each of the distribution stations during transportation of the pipeline comprises:
determining an initial solution according to the transportation plan;
and solving the time point of arrival of the product oil of each batch in the plurality of batches at each distribution station by using the transportation prediction model according to the initial solution.
3. The method of claim 2, wherein after determining the schedule during transportation of the product oil pipeline, the method further comprises:
checking the scheduling scheme;
under the condition that the scheduling scheme does not meet the preset requirement, correcting the current scheduling scheme according to the following modes:
randomly acquiring a plurality of groups of test schemes according to the current scheduling scheme;
respectively acquiring the path length corresponding to each group of test schemes in the plurality of groups of test schemes and the pheromone concentration corresponding to each group of test schemes in the plurality of groups of test schemes;
and selecting a test scheme meeting the requirements from the plurality of groups of test methods to replace the current scheduling scheme according to the path length corresponding to each group of test schemes in the plurality of groups of test schemes, and updating the pheromone concentration corresponding to the current scheduling scheme by using the pheromone concentration corresponding to the test scheme meeting the requirements.
4. The method of claim 1, wherein determining a dispatch plan during transportation of the product oil pipeline based on the points in time at which the product oil of each of the plurality of batches arrives at each of the distribution stations comprises:
and solving by using a mixed integer programming model according to the time point of the product oil of each batch in the plurality of batches reaching each fraction station so as to determine the dispatching scheme.
5. The method of claim 4, wherein the mixed integer programming model is built as follows:
acquiring characteristic parameters of a conveying pipeline;
and determining constraint conditions and an objective function according to the characteristic parameters so as to establish the mixed integer programming model.
6. A scheduling device for pipeline transportation is characterized by comprising:
the acquisition module is used for acquiring a historical scheduling scheme and historical demand data; wherein the historical demand data comprises: the demand quantity and the demand time of each sub-delivery station for each batch of product oil;
the establishing module is used for training by utilizing the historical scheduling scheme and the historical demand data to establish a transport prediction model;
the first determining module is used for determining the time point of the finished oil of each batch in the plurality of batches reaching each distribution station in the pipeline transportation process through the transportation prediction model;
the second determining module is used for determining a scheduling scheme in the transportation process of the finished oil pipeline according to the time point of the finished oil of each batch in the plurality of batches reaching each sub-transmission station;
the control module is used for controlling the transportation of each batch of the product oil in a plurality of batches in the transportation process of the product oil pipeline according to the scheduling scheme;
the time points of the finished oil of each batch in the multiple batches reaching each sub-delivery station in the pipeline transportation process determined by the transportation prediction model comprise the optimal time point sequence, and the time points of the finished oil of each batch in the multiple batches reaching each sub-delivery station are used for determining time constraint variables in the dispatching scheme;
wherein the constraint conditions at least comprise: injection constraints and pipeline state constraints; the injection constraints include: the injection flow is larger than a first threshold value, and the first threshold value is determined according to the relation between an oil mixing section in the transportation pipeline and the Reynolds number; the pipe state constraints include: limiting the occurrence and the stop of the transportation of the pipeline containing the oil mixing section;
the pipeline state constraint condition is specifically constructed according to the following formula:
wherein,for the first injection volume in the transport pipe,the amount of downloading of the ith station in the kth time window,the maximum flow rate of the ith pipe segment,the minimum flow rate when the ith pipe section is not mixed with oil,is the minimum flow rate when the oil mixture exists in the ith pipe section,is a binary variable for stopping conveying, if the ith pipe section stops conveying in the kth time windowOtherwise;Is a binary variable of mixed oil, if mixed oil exists in the ith pipe section in the kth time window and can not stop conveying,otherwise。
7. The apparatus of claim 6, wherein the first determining module comprises:
a first determination unit for determining an initial solution according to the transportation plan;
and the solving unit is used for solving the time point of the finished oil of each batch in the batches reaching each distribution station by using the transportation prediction model according to the initial solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810324141.7A CN108596457B (en) | 2018-04-12 | 2018-04-12 | Method and device for scheduling pipeline transportation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810324141.7A CN108596457B (en) | 2018-04-12 | 2018-04-12 | Method and device for scheduling pipeline transportation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108596457A CN108596457A (en) | 2018-09-28 |
CN108596457B true CN108596457B (en) | 2020-11-20 |
Family
ID=63621989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810324141.7A Active CN108596457B (en) | 2018-04-12 | 2018-04-12 | Method and device for scheduling pipeline transportation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108596457B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325425A (en) * | 2018-12-14 | 2020-06-23 | 顺丰科技有限公司 | Allocation scheme calculation method and device |
CN109740983A (en) * | 2018-12-26 | 2019-05-10 | 中国石油大学(北京) | A kind of product oil dispatching method and device based on pressure control |
CN114707716B (en) * | 2022-03-29 | 2024-01-05 | 中国石油大学(北京) | Method and system for optimizing scheduling of finished oil pipe network with transfer oil warehouse |
CN114862191B (en) * | 2022-05-07 | 2024-07-02 | 中国石油大学(北京) | Finished oil pipeline scheduling optimization method and system based on running stability |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8447423B2 (en) * | 2009-11-30 | 2013-05-21 | Exxonmobil Research And Engineering Company | Method and apparatus for optimizing a performance index of a bulk product blending and packaging plant |
CN106295995A (en) * | 2016-08-10 | 2017-01-04 | 曼威网络科技(上海)有限公司 | A kind of data analysing method for determining the production schedule and equipment |
-
2018
- 2018-04-12 CN CN201810324141.7A patent/CN108596457B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN108596457A (en) | 2018-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108596457B (en) | Method and device for scheduling pipeline transportation | |
CN105302096B (en) | Intelligent factory scheduling method | |
Mostafaei et al. | A novel monolithic MILP framework for lot-sizing and scheduling of multiproduct treelike pipeline networks | |
CN103606021B (en) | A kind of LNG receiving station dynamically stock forecast dispatching method | |
Akbari et al. | A new robust optimization approach for integrated multi-echelon, multi-product, multi-period supply chain network design under process uncertainty | |
Castro et al. | Batch-centric scheduling formulation for treelike pipeline systems with forbidden product sequences | |
CN103645705B (en) | A kind of LNG multiple spot cargo ship transport power forecast dispatching method | |
Moradi et al. | Robust scheduling for multi-product pipelines under demand uncertainty | |
Adhitya et al. | Heuristic rescheduling of crude oil operations to manage abnormal supply chain events | |
Wu et al. | A Petri net-based heuristic algorithm for realizability of target refining schedule for oil refinery | |
CN111582584B (en) | Air section operation time optimization method based on fairness of airlines | |
Cafaro et al. | Oil-derivatives pipeline logistics using discrete-event simulation | |
CN109409811A (en) | A kind of Logistic Scheduling method, apparatus, computer equipment and storage medium | |
US10282173B2 (en) | System and optimization method for oil programming in a refinery through linear genetic programming and grammar-oriented programming, and readable storage medium | |
Sharda et al. | Bottleneck analysis of a chemical plant using discrete event simulation | |
Liu et al. | Stochastic airline fleet assignment with risk aversion | |
Abdellaoui et al. | Multi-period optimal schedule of a multi-product pipeline: A case study in Algeria | |
CN105787597B (en) | Data optimization processing system | |
CN106909983A (en) | Based on many meteorological sources ultra-short term wind speed forecasting methods of Kalman filter and device | |
KR102147511B1 (en) | Method and apparatus for determining optimal production of petroleum products | |
CN109978299B (en) | Data analysis method and device for offshore wind power business and storage medium | |
CN103606020A (en) | Multipoint network type dynamic inter-station transfer forecasting dispatching method for LNG (Liquefied Natural Gas) receiving stations | |
Almeder et al. | A hybrid simulation optimization approach for supply chains | |
Cafaro et al. | Detailed scheduling of oil products pipelines with parallel batch inputs at intermediate sources | |
Relvas et al. | Pipeline scheduling and distribution centre management—A real-world scenario at CLC |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information |
Inventor after: Liang Yongtu Inventor after: Zhang Haoran Inventor after: Liao Qi Inventor after: Zhang Wan Inventor after: Nie Siming Inventor before: Zhang Haoran Inventor before: Liang Yongtu Inventor before: Liao Qi Inventor before: Zhang Wan Inventor before: Nie Siming |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |