Conveying pipeline control method, model training method, equipment and storage medium

Abstract

The invention discloses a conveying pipeline control method, a model training method, equipment and a storage medium, relates to the technical field of pipelines, and aims to provide an intelligent conveying pipeline control method to improve the control effect of an oil and gas conveying pipeline and ensure safe and stable operation of the oil and gas conveying pipeline. The method comprises the following steps: acquiring transmission demand data of a target pipeline reference area; determining a transmission demand type corresponding to the transmission demand data; the target pipeline reference area comprises at least one conveying pipeline; based on the transmission demand data and the transmission demand type, predicting an optimal operation data set of the target pipeline reference area; the operation data set comprises equipment operation data and pipeline operation data; generating a control strategy of the target pipeline reference area based on the optimal operation data set; the control strategy is used for controlling operation of the pipelines in the target pipeline reference area so as to meet the conveying requirement.

Description

Technical Field

[0001] This application relates to the technical field of pipelines, and particularly to a method for controlling a conveying pipeline, a method for training a model, a device, and a storage medium. Background Art

[0002] Pipelines are known as the major arteries of the country's energy. They are of great significance for ensuring the country's energy supply. Oil and gas pipelines have become an important means of transporting oil and gas resources in the national economic life. Due to the long length of oil and gas pipelines, numerous stations, and their close connection throughout the line, relying solely on on-site inspections by staff is labor-intensive and cannot accurately judge the status of all pipelines and equipment, thus unable to ensure the safe and stable operation of oil and gas pipelines.

[0003] In summary, the existing control effect of oil and gas pipelines is poor. Summary of the Invention

[0004] The purpose of this application is to provide a method for controlling a conveying pipeline, a method for training a model, a device, and a storage medium, so as to improve the control effect of oil and gas pipelines and ensure the safe and stable operation of oil and gas pipelines.

[0005] To achieve the above objective, this application adopts the following technical solutions:

[0006] In a first aspect, this application provides a method for controlling a conveying pipeline, including: obtaining the conveying demand data of a target pipeline reference area; and determining the conveying demand type corresponding to the conveying demand data; the target pipeline reference area includes at least one conveying pipeline; predicting the optimal operation data set of the target pipeline reference area based on the conveying demand data and the conveying demand type; the operation data set includes equipment operation data and pipeline operation data; generating a control strategy for the target pipeline reference area based on the optimal operation data set; the control strategy is used to control the operation of the pipelines within the target pipeline reference area to meet the conveying demand.

[0007] The method for controlling a conveying pipeline provided by this application accurately predicts the pipelines within the target pipeline area through the conveying demand data and the conveying demand type, obtains the optimal operation data set that can complete the conveying demand, realizes the automation of pipeline inspection and control, reduces the workload of staff, avoids the problem of poor accuracy in manual judgment, can improve the control effect of oil and gas pipelines, and ensure the safe and stable operation of oil and gas pipelines.

[0008] A possible implementation method is to input the optimal operation data prediction model to obtain the optimal operation data set of the target pipeline reference area; the optimal operation data prediction model is used to predict the optimal operation data set based on the conveying demand data of the pipeline reference area and the conveying demand type corresponding to the conveying demand data. Pipeline reference area Optimal operating data set for the domain, including: conveying demand data and conveying demand type Input the optimal operation data prediction model to obtain the optimal operation data set of the target pipeline reference area; the optimal operation data prediction model is used to predict the optimal operation data set based on the conveying demand data of the pipeline reference area and the conveying demand type corresponding to the conveying demand data.

[0009] Second aspect, a model training method of the present application, the method includes: obtaining a plurality of historical operation data groups of the target pipeline reference area under different transportation demand types; wherein, each historical operation data group includes historical pipeline operation data and historical equipment operation data; analyzing the plurality of historical operation data groups of the target pipeline reference area under different transportation demand types to obtain a plurality of historical operation evaluation values of the target pipeline reference area under different transportation demand types; for each transportation demand type among different transportation demand types, determining the optimal historical operation evaluation value of each transportation demand type, wherein the optimal historical operation evaluation value is the maximum value among the plurality of historical operation evaluation values; based on the transportation demand data of the target pipeline reference area, the transportation demand type corresponding to the transportation demand data, and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type, training the optimal operation data prediction model to be trained to obtain a trained optimal operation data prediction model.

[0010] A possible implementation manner, based on the transportation demand data of the target pipeline reference area, the transportation demand type corresponding to the transportation demand data, and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type, training the optimal operation data prediction model to be trained includes: using the transportation demand data of the target pipeline reference area and the transportation demand type corresponding to the transportation demand data as sample data, and using the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type as a sample label to form a training sample; training the optimal operation data prediction model to be trained based on the training sample.

[0011] Another possible implementation manner, before obtaining a plurality of historical operation data groups of the target pipeline reference area under different transportation demand types, the method further includes: obtaining the structural characteristics and transportation characteristics of the pipelines included in the pipeline reference structure diagram; the structural characteristics of the pipeline include at least one of the following: the number of sub-pipelines, the number of branch nodes; the transportation characteristics of the pipeline include at least one of the following: transportation efficiency, the number of transportation failures, the average value of the transportation failure influence coefficient; based on the structural characteristics and transportation characteristics of the pipeline, determining at least one target pipeline reference area and marking the range of at least one target pipeline reference area on the pipeline reference structure diagram.

[0012] Another possible implementation manner, based on the structural characteristics and transportation characteristics of the pipeline, determining at least one target pipeline reference area includes: obtaining at least one initial pipeline reference area based on the structural characteristics of the pipeline; for each initial pipeline reference area among the at least one initial pipeline reference area, correcting each initial pipeline reference area based on the transmission characteristics of the pipelines within each initial pipeline reference area to obtain at least one target pipeline reference area.

[0013] Another possible implementation manner is that the multiple historical operation data sets of the target pipeline reference area under different transportation demand types include multiple historical operation data sets of the target pipeline reference area in multiple historical transportation periods under each transportation demand type. Analyzing the multiple historical operation data sets of the target pipeline reference area under different transportation demand types to obtain multiple historical operation evaluation values of the target pipeline reference area under different transportation demand types, including: for each transportation demand type, comparing each historical pipeline operation data in the same historical transportation period with the preset pipeline operation data to obtain a first operation evaluation value; generating a first compensation coefficient according to the fluctuation range of all historical pipeline operation data in the same historical transportation period; comparing each historical equipment operation data in the same historical transportation period with the preset equipment operation data to obtain a second operation evaluation value; generating a second compensation coefficient according to the fluctuation range of all historical equipment operation data in the same historical transportation period; determining a third operation evaluation value according to the first operation evaluation value, the first compensation coefficient, the second operation evaluation value, and the second compensation coefficient; performing an averaging process on multiple third operation evaluation values in the same historical transportation period to obtain a fourth operation evaluation value; and obtaining a historical operation evaluation value based on the fourth operation evaluation values of multiple historical transportation periods.

[0014] In a third aspect, the present application provides an electronic device, which includes: a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method of the first aspect or the second aspect described above.

[0015] In a fourth aspect, the present application provides a chip, which is applied to an electronic device; the chip includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected by lines; the interface circuits are configured to receive signals from the memory of the electronic device and send signals to the processor of the electronic device, and the signals include software instructions stored in the memory. When the processor executes the software instructions, the electronic device executes the method of the first aspect or the second aspect described above.

[0016] In a fifth aspect, the present application provides a readable storage medium, which includes: software instructions; when the software instructions run in an electronic device, the electronic device implements the method of the first aspect or the second aspect described above.

[0017] In a sixth aspect, the present application provides a computer program product, when the computer program product runs on an electronic device, the electronic device executes the steps of the related method described in the first aspect or the second aspect to implement the method of the first aspect or the second aspect.

[0018] For the beneficial effects of the second aspect to the sixth aspect, refer to the corresponding descriptions of the first aspect, and details will not be repeated. Description of the Drawings

[0019] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic flow chart of a conveying pipeline control method provided by the present application;

[0021] Figure 2 It is a schematic flow chart of a model training method provided by the present application;

[0022] Figure 3 It is a schematic flow chart of another conveying pipeline control method provided by the present application;

[0023] Figure 4 It is a schematic diagram of the composition of a conveying pipeline control device provided by the present application;

[0024] Figure 5 It is a schematic diagram of the composition of a model training device provided by the present application;

[0025] Figure 6 It is a schematic diagram of the composition of an electronic device provided by the present application. Detailed implementation manners

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0027] In the embodiments of the present application, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, article or device. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, article or device including the element.

[0028] In the embodiments of the present application, words such as "exemplarily" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplarily" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplarily" or "for example" is intended to present relevant concepts in a specific manner.

[0029] In the description of this specification, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0030] Pipelines are known as the major arteries of the country's energy. They are of great significance for ensuring the country's energy supply. Oil and gas pipelines have become an important means of transporting oil and gas resources in the national economic life. Due to the long length of oil and gas pipelines, numerous stations and the close connection throughout the line, relying solely on on-site inspections by staff is labor-intensive and cannot accurately judge the status of all pipelines and equipment, thus unable to ensure the safe and stable operation of oil and gas pipelines.

[0031] Based on this, the pipeline transportation control method provided in the present application analyzes based on transportation demand data and transportation demand types, uses algorithms to accurately predict the target pipeline area, generates an optimal operation data set that meets the transportation requirements, and controls the pipelines in the target pipeline area to complete the transportation work according to the optimal operation data set. This method realizes the intelligence of pipeline inspection and regulation, effectively reduces the workload of staff, improves the judgment accuracy, thereby optimizing the oil and gas transportation control effect and ensuring the safe and stable operation of the pipeline system.

[0032] Exemplarily, the pipeline transportation control method of the present application can be executed by an electronic device.

[0033] Exemplarily, the electronic device can be a server. For example, a single server, or a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster.

[0034] Exemplarily, the electronic device can be a terminal device. For example, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, as well as a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) / virtual reality (VR) device, etc. The embodiments of the present application do not impose special restrictions on the specific form of the terminal device.

[0035] An embodiment of the present application provides a method for controlling a conveying pipeline, as Figure 1 shown, which specifically includes the following steps:

[0036] S11. Obtain the conveying demand data of the target pipeline reference area, and determine the conveying demand type corresponding to the conveying demand data.

[0037] Among them, the target pipeline reference area includes at least one conveying pipeline.

[0038] S12. Based on the conveying demand data and the conveying demand type, predict the optimal operation data set of the target pipeline reference area.

[0039] Among them, the operation data set includes equipment operation data and pipeline operation data.

[0040] In some embodiments, step S12 includes:

[0041] Input the conveying demand data and the conveying demand type into the optimal operation data prediction model to obtain the optimal operation data set of the target pipeline reference area.

[0042] Among them, the optimal operation data prediction model is used to predict the optimal operation data set based on the conveying demand data of the pipeline reference area and the conveying demand type corresponding to the conveying demand data.

[0043] S13. Based on the optimal operation data set, generate a control strategy for the target pipeline reference area.

[0044] In some embodiments, the control strategy is used to control the operation of the pipelines in the target pipeline reference area to meet the conveying demand.

[0045] An embodiment of the present application provides a model training method, as Figure 2 shown, which specifically includes the following steps:

[0046] S21. Obtain multiple historical operation data sets of the target pipeline reference area under different conveying demand types.

[0047] Among them, each historical operation data set includes historical pipeline operation data and historical equipment operation data.

[0048] Exemplarily, step S21 includes:

[0049] Obtain multiple historical conveying time periods of the target pipeline reference area under each conveying demand type; and obtain the historical pipeline operation data and historical equipment operation data collected by different data acquisition nodes in each historical conveying time period of the target pipeline reference area.

[0050] S22. Analyze multiple historical operation data groups of the target pipeline reference area under different types of conveying requirements to obtain multiple historical operation evaluation values of the target pipeline reference area under different types of conveying requirements.

[0051] S23. For each type of conveying requirement among different types of conveying requirements, determine the optimal historical operation evaluation value of each type of conveying requirement.

[0052] Among them, the optimal historical operation evaluation value is the maximum value among multiple historical operation evaluation values.

[0053] S24. Based on the conveying requirement data of the target pipeline reference area, the type of conveying requirement corresponding to the conveying requirement data, and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the type of conveying requirement, train the optimal operation data prediction model to be trained to obtain a trained optimal operation data prediction model.

[0054] Exemplarily, sort the historical operation evaluation values of the same type of conveying requirement, and set the historical equipment operation data and historical pipeline operation data corresponding to the historical operation evaluation value ranked first as the optimal historical operation data group of the corresponding type of conveying requirement, and generate a mapping table of type of conveying requirement - optimal historical operation data group.

[0055] Exemplarily, train the optimal operation data prediction model to be trained based on the data in the mapping table of type of conveying requirement - optimal historical operation data group.

[0056] In some embodiments, step S24 includes:

[0057] A1. Use the conveying requirement data of the target pipeline reference area and the type of conveying requirement corresponding to the conveying requirement data as sample data, and use the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the type of conveying requirement as a sample label to form a training sample.

[0058] A2. Train the optimal operation data prediction model to be trained based on the training sample.

[0059] In some embodiments, before step S21, the method further includes:

[0060] B1. Obtain the structural features and conveying features of the pipelines included in the pipeline reference structure diagram.

[0061] In some embodiments, the structural features of the pipeline include at least one of the following: the number of sub - pipelines, the number of branch nodes; the conveying features of the pipeline include at least one of the following: conveying efficiency, the number of conveying failures, the average value of the conveying failure influence coefficient.

[0062] In some embodiments, a reference diagram of the oil and gas pipeline structure is constructed, which includes multiple data acquisition nodes; the structural characteristics of the pipeline are obtained through the reference diagram of the oil and gas pipeline structure; and the transportation characteristics of the pipeline are obtained through the data acquisition nodes.

[0063] Exemplarily, based on the length of the pipeline, the main pipeline route, and the structural relationship between the pipeline branch routes in the reference diagram of the oil and gas pipeline structure, the oil and gas pipeline is divided into multiple concerned sub-pipelines, and the structural characteristics of different regions are constructed according to the number of concerned sub-pipelines and the number of branch nodes.

[0064] Exemplarily, according to the pipeline length, pipe diameter, oil and gas transportation volume within a preset time period, and average transportation pressure of each concerned sub-pipeline, the transportation efficiency of the corresponding concerned sub-pipeline within the preset time period is generated.

[0065] Exemplarily, the transportation fault log of each concerned sub-pipeline within the preset time period is obtained, and the number of transportation faults and the average value of the transportation fault impact coefficient of the corresponding concerned sub-pipeline are determined according to the transportation fault log.

[0066] Exemplarily, the transportation characteristics of each region in the reference diagram of the oil and gas pipeline structure are constructed according to the transportation efficiency, the number of transportation faults, and the average value of the transportation fault impact coefficient of each concerned sub-pipeline.

[0067] B2. Based on the structural characteristics and transportation characteristics of the pipeline, at least one target pipeline reference area is determined, and the range of at least one target pipeline reference area is marked on the pipeline reference structure diagram.

[0068] In some embodiments, step B2 includes:

[0069] B21. Based on the structural characteristics of the pipeline, at least one initial pipeline reference area is obtained.

[0070] Exemplarily, if the number of concerned sub-pipelines in the structural characteristics of the area is greater than a preset first quantity threshold or the number of branch nodes is greater than a preset second quantity threshold, then this area is set as an initial pipeline reference area.

[0071] B22. For each initial pipeline reference area in at least one initial pipeline reference area, each initial pipeline reference area is corrected based on the transmission characteristics of the pipelines within each initial pipeline reference area to obtain at least one target pipeline reference area.

[0072] Exemplarily, the transportation characteristics of the corresponding initial pipeline reference area are constructed according to the transportation efficiency, the number of transportation faults, and the average value of the transportation fault impact coefficient of each concerned sub-pipeline within the same initial pipeline reference area; a regional correction coefficient is set according to the transportation characteristics of the initial pipeline reference area; and the initial pipeline reference area is corrected according to the regional correction coefficient to obtain the target pipeline reference area.

[0073] Exemplarily, the conveying feature satisfies the following formula (1):

[0074]

[0075] where T is the conveying feature, a1 is the first weight coefficient, a2 is the second weight coefficient, n is the number of concerned sub-pipelines in the same initial pipeline reference area, gi is the number of conveying failures of the i-th concerned sub-pipeline, yi is the average value of the conveying failure impact coefficients of the i-th concerned sub-pipeline, and pi is the conveying efficiency of the i-th concerned sub-pipeline.

[0076] Exemplarily, four conveying feature intervals are preset in advance: the first preset conveying feature interval, the second preset conveying feature interval, the third preset conveying feature interval, and the fourth preset conveying feature interval; four preset area correction coefficients are preset in advance: the first preset area correction coefficient, the second preset area correction coefficient, the third preset area correction coefficient, and the fourth preset area correction coefficient.

[0077] For example, when calculating the conveying feature according to formula (1), when the conveying feature is in the first preset conveying feature interval, the area correction coefficient of the corresponding initial pipeline reference area is set as the fourth preset area correction coefficient; when the conveying feature is in the second preset conveying feature interval, the area correction coefficient of the corresponding initial pipeline reference area is set as the third preset area correction coefficient; when the conveying feature is in the third preset conveying feature interval, the area correction coefficient of the corresponding initial pipeline reference area is set as the second preset area correction coefficient; when the conveying feature is in the fourth preset conveying feature interval, the area correction coefficient of the corresponding initial pipeline reference area is set as the first preset area correction coefficient.

[0078] In some embodiments, before step S22, the method further includes:

[0079] C1. Extract the conveying demand data corresponding to multiple historical operation data groups.

[0080] C2. Analyze the conveying demand data of multiple different historical conveying time periods to obtain multiple conveying demand types.

[0081] C3. Perform a conveying demand correlation analysis on the historical operation data groups of different conveying demand types of each data acquisition node to obtain the historical operation data groups of each data acquisition node in each conveying demand type. Among them, the historical operation data group includes: historical pipeline operation data and historical equipment operation data.

[0082] Exemplarily, step C3 includes:

[0083] C31. Obtain the conveying demand data, historical pipeline operation data, and historical equipment operation data of each data acquisition node under different conveying demand types during the historical conveying period, and construct the change curve of the conveying demand data, multiple change curves of the historical pipeline operation data, and multiple change curves of the historical equipment operation data corresponding to the historical conveying period;

[0084] Obtain the sequence M of change time nodes in the change curve of the conveying demand data of different conveying demand types, M(M1, M2, … Mf), where Ms is the s-th change time node, and set the change weight of each change time node respectively.

[0085] C32. Generate the degree of association between the corresponding historical pipeline operation data and historical equipment operation data and the conveying demand type according to the degree of change of each historical pipeline operation data change curve and each historical equipment operation data change curve at multiple change time nodes.

[0086] Exemplarily, the degree of association satisfies formula (2):

[0087]

[0088] where W is the degree of association, f is the number of change time nodes, bs is the degree of change of the s-th change time node, and cs is the change weight of the s-th change time node.

[0089] C33. Set the historical pipeline operation data and historical equipment operation data with the degree of association greater than the preset degree of association threshold as the historical pipeline operation data and historical equipment operation data corresponding to the conveying demand type.

[0090] In some embodiments, when the multiple historical operation data groups of the target pipeline reference area under different conveying demand types include: multiple historical operation data groups of multiple historical conveying periods of the target pipeline reference area under each conveying demand type, step S22 includes:

[0091] D1. For each conveying demand type, compare each historical pipeline operation data of the same historical conveying period with the preset pipeline operation data to obtain the first operation evaluation value; generate the first compensation coefficient according to the fluctuation range of all historical pipeline operation data of the same historical conveying period.

[0092] D2. Compare each historical equipment operation data of the same historical conveying period with the preset equipment operation data to obtain the second operation evaluation value; generate the second compensation coefficient according to the fluctuation range of all historical equipment operation data of the same historical conveying period.

[0093] D3. Determine the third operation evaluation value based on the first operation evaluation value, the first compensation coefficient, the second operation evaluation value, and the second compensation coefficient.

[0094] D4. Perform an averaging process on multiple third operation evaluation values for the same historical transportation period to obtain the fourth operation evaluation value.

[0095] D5. Obtain the historical operation evaluation value based on the fourth operation evaluation values of multiple historical transportation periods.

[0096] The following introduces the pipeline transportation control method provided by this application with a specific embodiment.

[0097] As Figure 3 shown, it specifically includes the following steps:

[0098] S31. Construct a reference diagram of the oil and gas pipeline structure.

[0099] S32. Obtain the transportation characteristics and structural characteristics of the pipeline, divide them into multiple target pipeline reference areas according to the transportation characteristics and structural characteristics, and map them on the reference diagram of the oil and gas pipeline structure.

[0100] S33. Obtain multiple historical pipeline operation data and historical equipment operation data of the data acquisition nodes within the pipeline reference area, analyze the multiple historical pipeline operation data and historical equipment operation data, and obtain multiple historical operation evaluation values of the pipeline reference area under different transportation demand types.

[0101] S34. Sort the historical operation evaluation values of the same transportation demand type, determine the optimal historical operation data group corresponding to the transportation demand type, and train the optimal operation data prediction model based on multiple optimal historical operation data groups.

[0102] S35. Generate the predicted optimal operation data group corresponding to the pipeline reference area based on the optimal operation data prediction model, and generate the control strategy corresponding to the pipeline reference area based on the predicted optimal operation data group.

[0103] This application improves the control effect of the oil and gas pipeline by constructing a reference diagram of the oil and gas pipeline structure and dividing multiple target pipeline reference areas, calculates the operation evaluation values of each target pipeline reference area under different transportation demand types, screens out the optimal operation data group under each transportation demand type according to the operation evaluation values, and constructs the optimal operation data generation model corresponding to the target pipeline reference area to obtain the predicted optimal operation data group of each target pipeline reference area, which can accurately judge the pipeline state and equipment state and ensure the safe and stable operation of the oil and gas pipeline.

[0104] Figure 4The present application provides a conveying pipeline control device. The conveying pipeline control device 400 includes: an acquisition module 401, a prediction module 402, and a control module 403. Among them, the acquisition module 401 is configured to: acquire the conveying demand data of the target pipeline reference area; and determine the conveying demand type corresponding to the conveying demand data. The target pipeline reference area includes at least one conveying pipeline. The prediction module 402 is configured to predict the optimal operation data set of the target pipeline reference area based on the conveying demand data and the conveying demand type. The operation data set includes equipment operation data and pipeline operation data. The control module 403 is configured to: generate a control strategy for the target pipeline reference area based on the optimal operation data set. The control strategy is used to control the operation of the pipelines in the target pipeline reference area to meet the conveying demand.

[0105] A possible implementation manner is that the prediction module 402 is specifically configured to: input the conveying demand data and the conveying demand type into the optimal operation data prediction model to obtain the optimal operation data set of the target pipeline reference area. The optimal operation data prediction model is used to predict the optimal operation data set based on the conveying demand data of the pipeline reference area and the conveying demand type corresponding to the conveying demand data.

[0106] Figure 5 The present application provides a model training device. The model training device 500 includes: an acquisition module 501, an analysis module 502, and a training module 503. Among them, the acquisition module 501 is configured to: acquire multiple historical operation data sets of the target pipeline reference area under different conveying demand types. Each historical operation data set includes historical pipeline operation data and historical equipment operation data. The analysis module 502 is configured to: analyze the multiple historical operation data sets of the target pipeline reference area under different conveying demand types to obtain multiple historical operation evaluation values of the target pipeline reference area under different conveying demand types. For each conveying demand type among different conveying demand types, determine the optimal historical operation evaluation value of each conveying demand type, where the optimal historical operation evaluation value is the maximum value among the multiple historical operation evaluation values. The training module 503 is configured to: train the optimal operation data prediction model to be trained based on the conveying demand data of the target pipeline reference area, the conveying demand type corresponding to the conveying demand data, and the optimal historical operation data set corresponding to the optimal historical operation evaluation value of the conveying demand type to obtain the trained optimal operation data prediction model.

[0107] A possible implementation manner is that the training module 503 is specifically configured to: use the conveying demand data of the target pipeline reference area and the conveying demand type corresponding to the conveying demand data as sample data, and use the optimal historical operation data set corresponding to the optimal historical operation evaluation value of the conveying demand type as a sample label to form a training sample. Train the optimal operation data prediction model to be trained based on the training sample.

[0108] In another possible implementation manner, the obtaining module 501 is further configured to: obtain the structural features and conveying features of the pipelines included in the pipeline reference structure diagram; the structural features of the pipelines include at least one of the following: the number of sub-pipelines, the number of branch nodes; the conveying features of the pipelines include at least one of the following: conveying efficiency, the number of conveying failures, the average value of the conveying failure influence coefficient; based on the structural features and conveying features of the pipelines, determine at least one target pipeline reference area, and mark the range of at least one target pipeline reference area on the pipeline reference structure diagram.

[0109] In yet another possible implementation manner, the obtaining module 501 is specifically configured to: obtain at least one initial pipeline reference area based on the structural features of the pipelines; for each initial pipeline reference area in the at least one initial pipeline reference area, correct each initial pipeline reference area based on the transmission features of the pipelines within each initial pipeline reference area, so as to obtain at least one target pipeline reference area.

[0110] In yet another possible implementation manner, the multiple historical operation data groups of the target pipeline reference area under different conveying demand types include the multiple historical operation data groups of the multiple historical conveying time periods of the target pipeline reference area under each conveying demand type. The analysis module 502 is specifically configured to: for each conveying demand type, compare each historical pipeline operation data of the same historical conveying time period with the preset pipeline operation data to obtain a first operation evaluation value; generate a first compensation coefficient according to the fluctuation range of all the historical pipeline operation data of the same historical conveying time period; compare each historical equipment operation data of the same historical conveying time period with the preset equipment operation data to obtain a second operation evaluation value; generate a second compensation coefficient according to the fluctuation range of all the historical equipment operation data of the same historical conveying time period; determine a third operation evaluation value according to the first operation evaluation value, the first compensation coefficient, the second operation evaluation value, and the second compensation coefficient; perform an averaging process on the multiple third operation evaluation values of the same historical conveying time period to obtain a fourth operation evaluation value; and obtain a historical operation evaluation value based on the fourth operation evaluation values of the multiple historical conveying time periods.

[0111] In the case of implementing the functions of the above integrated modules in the form of hardware, an embodiment of the present disclosure provides a possible structure of the electronic device involved in the above embodiments. As Figure 6 shown, the electronic device 600 includes: a processor 602, a bus 604. Optionally, the electronic device 600 may further include a memory 601; optionally, the electronic device 600 may further include a communication interface 603.

[0112] The processor 602 can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present application. The processor 602 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present disclosure. The processor 602 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0113] The communication interface 603 is used to connect to other devices through a communication network. The communication network can be an Ethernet, a wireless access network, a wireless local area network (WLAN), etc.

[0114] The memory 601 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0115] As a possible implementation, the memory 601 can exist independently of the processor 602. The memory 601 can be connected to the processor 602 through a bus 604 for storing instructions or program codes. When the processor 602 calls and executes the instructions or program codes stored in the memory 601, it can implement the functions involved in the pipeline control method provided by the embodiments of the present application. In another possible implementation, the memory 601 can also be integrated with the processor 602.

[0116] The bus 604 can be an extended industry standard architecture (EISA) bus, etc. The bus 604 can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0117] In an exemplary embodiment, the embodiment of the present application further provides a readable storage medium, on which program instructions are stored; when the program instructions are executed by an electronic device, the electronic device is enabled to implement the method described in the foregoing embodiment. The readable storage medium may be a non-transitory readable storage medium. For example, the non-transitory readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0118] In an exemplary embodiment, the embodiment of the present application further provides a computer program product. When the computer program product runs on an electronic device, the electronic device is enabled to execute the above-mentioned related method steps to implement the functions involved in the conveying pipeline control method in the above embodiment.

[0119] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for controlling a conveying pipeline, characterized in that: The method comprises: Acquire the transportation demand data of the target pipeline reference area, and determine the transportation demand type corresponding to the transportation demand data; the target pipeline reference area includes at least one transportation pipeline; Based on the transportation demand data and the transportation demand type, predicting an optimal operation data group of the target pipeline reference area; the operation data group includes equipment operation data and pipeline operation data; Based on the optimal operation data set, a control strategy for the target pipeline reference area is generated; the control strategy is used to control the operation of the pipeline in the target pipeline reference area to meet the transportation demand.

2. The method according to claim 1, characterized in that The step of predicting the optimal operation data group of the target pipeline reference area based on the transportation demand data and the transportation demand type includes: The transportation demand data and the transportation demand type are input into an optimal operation data prediction model to obtain an optimal operation data group for the target pipeline reference area; the optimal operation data prediction model is used to predict the optimal operation data group based on the transportation demand data of the pipeline reference area and the transportation demand type corresponding to the transportation demand data.

3. A model training method, characterized in that: The method comprises: Acquire multiple historical operation data groups under different types of transportation demand in the target pipeline reference area; wherein each of the historical operation data groups includes historical pipeline operation data and historical equipment operation data; Analyzing a plurality of historical operation data groups of the target pipeline reference area under the different types of transportation demands to obtain a plurality of historical operation evaluation values ​​of the target pipeline reference area under the different types of transportation demands; For each of the different transport demand types, determining an optimal historical operation evaluation value of each of the transport demand types, wherein the optimal historical operation evaluation value is a maximum value among the multiple historical operation evaluation values; Based on the transportation demand data of the target pipeline reference area, the transportation demand type corresponding to the transportation demand data and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type, the optimal operation data prediction model to be trained is trained to obtain the trained optimal operation data prediction model.

4. The method according to claim 3, characterized in that The optimal operation data prediction model to be trained is trained based on the transportation demand data of the target pipeline reference area, the transportation demand type corresponding to the transportation demand data, and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type, including: The transportation demand data of the target pipeline reference area and the transportation demand type corresponding to the transportation demand data are used as sample data, and the optimal historical operation data group corresponding to the optimal historical operation evaluation value of the transportation demand type is used as a sample label to form a training sample; The optimal operation data prediction model to be trained is trained based on the training samples.

5. The method according to claim 3, characterized in that: Before obtaining a plurality of historical operation data groups of the target pipeline reference area under different types of transportation requirements, the method further includes: Acquire the structural features and transportation features of the pipeline included in the pipeline reference structure diagram; the structural features of the pipeline include at least one of the following: the number of sub-pipelines and the number of branch nodes; the transportation features of the pipeline include at least one of the following: transportation efficiency, number of transportation failures, and mean value of transportation failure influence coefficient; Based on the structural characteristics and transportation characteristics of the pipeline, at least one target pipeline reference area is determined, and the range of the at least one target pipeline reference area is marked on the pipeline reference structure diagram.

6. The method according to claim 5, characterized in that The step of determining at least one target pipeline reference area based on the structural characteristics and the transport characteristics of the pipeline comprises: Based on the structural characteristics of the pipeline, obtaining at least one initial pipeline reference region; For each of the at least one initial pipeline reference region, each initial pipeline reference region is corrected based on the transmission characteristics of the pipeline in each initial pipeline reference region to obtain at least one target pipeline reference region.

7. The method according to claim 3, characterized in that The plurality of historical operation data groups of the target pipeline reference area under the different transport demand types include a plurality of historical operation data groups of the target pipeline reference area under each transport demand type in a plurality of historical transport time periods; The analyzing of the multiple historical operation data groups of the target pipeline reference area under the different transportation demand types to obtain multiple historical operation evaluation values ​​of the target pipeline reference area under the different transportation demand types includes: For each type of transportation demand, each historical pipeline operation data of the same historical transportation period is compared with the preset pipeline operation data to obtain a first operation evaluation value; a first compensation coefficient is generated according to the fluctuation range of all historical pipeline operation data of the same historical transportation period; Compare each historical equipment operation data of the same historical transportation period with the preset equipment operation data to obtain a second operation evaluation value; generate a second compensation coefficient according to the fluctuation range of all historical equipment operation data of the same historical transportation period; determining a third operation evaluation value according to the first operation evaluation value, the first compensation coefficient, the second operation evaluation value, and the second compensation coefficient; Performing average processing on a plurality of third operation evaluation values ​​of the same historical transportation period to obtain a fourth operation evaluation value; The historical operation evaluation value is obtained based on the fourth operation evaluation values ​​of the plurality of historical transport time periods.

8. An electronic device, characterized in that: The electronic device includes: a processor and a memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 2 or any one of claims 3 to 7.

9. A readable storage medium, characterized in that: The readable storage medium includes: software instructions; When the software instructions are executed in an electronic device, the electronic device implements the method according to any one of claims 1 to 2 or any one of claims 3 to 7.

10. A computer program product, characterized in that The computer program product comprises: computer instructions; When the computer instructions are executed in an electronic device, the electronic device implements the method according to any one of claims 1 to 2 or any one of claims 3 to 7.

Images