A method, device, electronic device and medium for tracking the position of an oil-mixing interface

Abstract

The present invention relates to a method, device, electronic device, and medium for tracking the position of a mixed oil interface. The method comprises: obtaining operating data on the position of the mixed oil interface of a pipeline to be tested, the operating data comprising the flow velocity of the pipeline section, the density of the preceding oil product, the density of the succeeding oil product, the temperature at the starting point of the pipeline section, and the temperature at the ending point of the pipeline section; obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the operating data of the mixed oil interface position and a pre-trained inter-station interface reduced flow velocity determination model, the inter-station interface reduced flow velocity determination model being trained based on historical mixed oil interface position operating data; and determining the position of the tested mixed oil interface corresponding to the pipeline to be tested based on the target inter-station interface reduced flow velocity. The method of the present invention can accurately determine the position of the tested mixed oil interface based on the inter-station interface reduced flow velocity determination model trained based on the historical mixed oil interface position operating data.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a method, device, electronic equipment and medium for tracking the position of an oil-mixing interface. Background Art

[0002] The operation of stations along refined oil pipelines relies on precise batch interface tracking. The key to batch tracking using theoretical or empirical formulas lies in the dynamic calculation of the oil-product interface position and the length of the mixed oil. Typically, mixed oil batch tracking employs a Lagrangian coordinate system. The coordinate system's origin position (the location of the mixed oil interface) and the mixed oil length (or concentration distribution) are used to reflect the development and movement of the mixed oil interface, providing data support for station operations.

[0003] At present, scholars have carried out a large number of computational studies on the length of mixed oil and the distribution of mixed oil concentration, and have obtained a relatively high-precision characterization method. However, the precise tracking of the batch interface may depend more on the calculation of the origin position of the coordinate system (the position of the mixed oil interface). The theoretical calculation of the batch interface position needs to be determined based on the volume of oil injected into the pipeline and the pipe capacity of the pipeline, that is, L = Qt / A, where t is the time required for the interface position to run from the starting point of the pipe section to the end point of the pipe section, L is the total mileage of the pipe section, A is the cross-sectional area of ​​the pipe section, and Q is the flow rate of the pipe section. Some technicians have also tried to introduce the effects of temperature and pressure on the expansion / contraction of the oil volume to improve the calculation accuracy of t. However, the measurement error of the pipeline flowmeter itself may cause a significant offset in the calculation result of t.

[0004] If the pipeline flowmeter has a relative error of 1%, then when the oil-mixing interface reaches the end point, the interface position calculated using L = Qt / A will also have a relative deviation of 1% from the total length of the pipeline section. For example, if a 50km pipeline has a 1000m long oil-mixing section at the end point, a 10% error in the calculated length of the section will result in an absolute error of 100m. If the relative error in the coordinate system origin position (the oil-mixing interface position) is 1%, the absolute error will be 500m. Therefore, accurate calculation of the coordinate system origin position (the oil-mixing interface position) is crucial for precise batch interface tracking.

[0005] As can be seen from the above, SCADA data is required for batch tracking of refined oil products. However, SCADA data inevitably contains certain measurement errors, which can cause significant deviations in batch tracking. However, under different operating conditions and environmental conditions, pipeline conditions vary, and oil properties vary. Simply relying on SCADA systems to obtain data and then regress flowmeter data cannot meet the required accuracy for tracking mixed oil interfaces under complex operating conditions. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a method, device, electronic device and medium for tracking the position of an oil-mixing interface, aiming to solve at least one of the above technical problems.

[0007] The present invention solves the above technical problems with the following technical solutions: a method for tracking the position of an oil-mixing interface, the method comprising:

[0008] Obtaining the oil-mixing interface position operating data of the pipeline to be tested, wherein the oil-mixing interface position operating data includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section;

[0009] Obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data;

[0010] The position of the oil-mixing interface to be measured corresponding to the pipeline to be measured is determined according to the converted flow velocity of the target station interface.

[0011] The beneficial effect of the present invention is that after obtaining the operating data of the oil-mixing interface position of the pipeline to be tested, the target inter-station interface reduced flow velocity corresponding to the pipeline to be tested is determined by using the pre-trained inter-station interface reduced flow velocity determination model. Since the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data, it can truly reflect the inter-station interface reduced flow velocity. Therefore, the target inter-station interface reduced flow velocity determined by the inter-station interface reduced flow velocity determination model is more accurate. Furthermore, based on the target inter-station interface reduced flow velocity, the position of the oil-mixing interface to be tested corresponding to the pipeline to be tested is determined more accurately.

[0012] On the basis of the above technical solution, the present invention can also be improved as follows.

[0013] Furthermore, the above-mentioned inter-station interface reduced velocity determination model is trained in the following way:

[0014] Acquire a training sample, the training sample including a plurality of sample data corresponding to a sample pipeline, the plurality of sample data being data corresponding to the sample pipeline at different flow platform periods, the training sample including historical oil-mixing interface position operation data of the sample pipeline, each of the sample data including pipeline flow rate, forward oil product density, backward oil product density, pipe section starting point temperature, and pipe section ending point temperature, each of the sample data corresponding to a real inter-station interface converted flow rate;

[0015] The initial model is trained according to the training samples to obtain the predicted inter-station interface converted flow velocity corresponding to each sample data;

[0016] Determining the objective function of the initial model according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data;

[0017] If the objective function meets the preset training end condition, the initial model when the training end condition is met will be used as the model for determining the interface converted flow velocity between stations; if the overall objective function does not meet the preset training end condition, the model parameters of the initial model will be adjusted, and the initial model will be retrained according to the adjusted model parameters until the objective function meets the preset training end condition.

[0018] The beneficial effect of adopting the above further scheme is that the inter-station interface reduced flow rate determination model is obtained by training multiple sample data corresponding to the sample pipeline. The multiple sample data are determined based on historical mixed oil interface position operation data, which can reflect the actual inter-station interface reduced flow rate corresponding to the sample pipeline in different flow platform time periods, so that the determined inter-station interface reduced flow rate determination model can meet actual needs.

[0019] Furthermore, the sample pipeline includes multiple flow platforms, and the method further includes:

[0020] For each sample data, obtaining the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform;

[0021] The initial model is trained based on the training samples to obtain the predicted station-to-station interface converted flow velocity corresponding to each sample data, including:

[0022] The initial model is trained according to the training samples to obtain the predicted flow platform converted flow velocity corresponding to each flow platform in each sample data when the 50% concentration interface passes through the sample data;

[0023] The overall objective function of the initial model is determined based on the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data, including:

[0024] For each sample data, determining the initial objective function of the initial model according to the actual flow platform converted flow rate and the predicted flow platform converted flow rate corresponding to the sample data;

[0025] The overall objective function of the initial model is determined according to the objective functions corresponding to the respective sample data.

[0026] The beneficial effect of this further approach is that when a batch of oil is transported within a pipeline, the flow rate of the oil changes periodically due to the distribution or unloading action, forming multiple flow rate platforms with different flow rates. Therefore, using the flow rate corresponding to each flow rate platform period as training samples for training can achieve higher accuracy in the determined model.

[0027] Furthermore, for each sample data, the above-mentioned obtaining of the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform includes:

[0028] Obtaining the instantaneous flow rate corresponding to the 50% concentration interface in the sample pipeline, the total length of time the 50% concentration interface passes through the sample pipeline, and the start and end times corresponding to the 50% concentration interface passing through each flow platform;

[0029] For each of the traffic platforms, determining a first average traffic corresponding to the traffic platform according to the total time length, the instantaneous traffic, and the start time and end time corresponding to the traffic platform;

[0030] Determining a second average flow rate at which a 50% concentration interface passes through the sample pipe within the total time period based on the instantaneous flow rate and the total time period;

[0031] For each of the flow platforms, the real flow platform converted flow rate corresponding to the 50% concentration interface passing through each of the flow platforms is determined based on the real inter-station interface converted flow rate corresponding to the sample data, the first average flow rate and the second average flow rate corresponding to the flow platform.

[0032] The beneficial effect of adopting the above further scheme is that the converted flow rate of the real flow platform corresponding to each of the above flow platforms can be determined based on the instantaneous flow corresponding to the 50% concentration interface in the sample pipeline, the total length of time the 50% concentration interface passes through the sample pipeline, and the start time and end time corresponding to the 50% concentration interface passing through each of the flow platforms.

[0033] Furthermore, for each sample data, the actual inter-station interface converted velocity corresponding to the sample data is determined by the following method:

[0034] Acquiring the length of the sample channel, a first time when a 50% concentration interface passes through a starting point of the sample channel, and a second time when a 50% concentration interface passes through an end point of the sample channel;

[0035] A first converted flow rate corresponding to a 50% concentration interface is determined according to the pipeline length, the first time, and the second time, and the first converted flow rate is used as the actual inter-station interface converted flow rate corresponding to the sample data.

[0036] The beneficial effect of adopting the above further solution is that the actual inter-station interface converted flow velocity corresponding to each sample data is determined in the above manner, providing data support for subsequent use.

[0037] Furthermore, the pipeline to be tested includes multiple flow platforms. The model is determined based on the operating data of the oil-mixing interface position and the pre-trained inter-station interface reduced flow rate to obtain the target inter-station interface reduced flow rate corresponding to the pipeline to be tested, including:

[0038] A model is determined based on the operating data of the oil-mixing interface position and a pre-trained inter-station interface reduced flow rate, to obtain a target inter-station interface reduced flow rate corresponding to a target flow platform of the oil-mixing interface to be tested corresponding to the pipeline to be tested, wherein the plurality of flow platforms include the target flow platform, and the target flow platform is the flow platform currently passed by the oil-mixing interface to be tested;

[0039] The above-mentioned determining the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow velocity of the target station interface includes:

[0040] Obtaining the start time and end time corresponding to the oil mixture interface to be tested passing through the target flow platform;

[0041] The position of the tested mixed oil interface corresponding to the tested pipeline is determined according to the converted flow rate of the target station interface corresponding to the tested mixed oil interface at the target flow platform and the start time and end time corresponding to the tested mixed oil interface.

[0042] The beneficial effect of adopting the above further solution is that when determining the position of the mixed oil interface to be measured, not only the converted flow rate of the interface between the target stations is taken into account, but also the start time and end time corresponding to the passage of the mixed oil interface to be measured through the target flow platform are taken into account, which can make the position of the mixed oil interface to be measured determined more accurately.

[0043] Furthermore, for each sample data, the initial objective function corresponding to the sample data is determined in the following manner:

[0044] For each of the sample data, based on the sample data and the reduced flow rates of each real flow platform corresponding to the sample data, determine a mean matrix and a covariance matrix corresponding to the sample data, wherein the mean matrix represents the relationship between the mean corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the mean corresponding to each historical oil-mixing interface position operating data in the sample data, and the covariance matrix represents the relationship between the covariance corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the covariance corresponding to each historical oil-mixing interface position operating data in the sample data;

[0045] For each sample data, an initial loss value corresponding to the sample data is calculated using a likelihood function according to the mean matrix and the covariance matrix.

[0046] The beneficial effect of adopting the above further scheme is that the covariance matrix and the mean matrix can more accurately reflect the relationship between the mean corresponding to the converted flow rate of each real flow platform corresponding to the sample data and the mean and covariance corresponding to the operating data of each historical mixed oil interface position in the sample data.

[0047] In a second aspect, in order to solve the above technical problems, the present invention further provides a device for tracking the position of an oil-mixing interface, the device comprising:

[0048] A data acquisition module is used to obtain the operating data of the oil-mixing interface position of the pipeline to be tested, wherein the operating data of the oil-mixing interface position includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section;

[0049] a target inter-station interface reduced flow velocity determination module, configured to obtain the target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data;

[0050] The oil-mixing interface position determination module is used to determine the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow rate of the target station interface.

[0051] In a third aspect, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the oil mixing interface position tracking method of the present application is implemented.

[0052] In a fourth aspect, in order to solve the above technical problems, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for tracking the position of the oil-mixing interface of the present application is implemented.

[0053] Additional aspects and advantages of the present application will be given in part in the following description, which will become apparent from the following description, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention.

[0055] Figure 1A schematic flow chart of a method for tracking the position of an oil-mixing interface provided by one embodiment of the present invention;

[0056] Figure 2 A schematic structural diagram of a device for tracking the position of an oil-mixing interface provided by one embodiment of the present invention;

[0057] Figure 3 The present invention provides a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0059] The following describes in detail the technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems using specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following embodiments of the present invention are described in conjunction with the accompanying drawings.

[0060] The solution provided by the embodiments of the present invention is applicable to any application scenario requiring tracking of the oil-mixing interface. It can be executed by any electronic device, such as a user's terminal device, including at least one of the following: a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, smart TV, or smart in-vehicle device.

[0061] The embodiment of the present invention provides a possible implementation method, such as Figure 1 As shown in FIG, a flow chart of a method for tracking the position of a mixed oil interface is provided. The solution can be executed by any electronic device, for example, a terminal device, or by a terminal device and a server. For ease of description, the method provided by the embodiment of the present invention will be described below using a server as an example execution subject. Figure 1 As shown in the flowchart, the method may include the following steps:

[0062] Step S110, obtaining the oil-mixing interface position operating data of the pipeline to be tested, wherein the oil-mixing interface position operating data includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section;

[0063] Step S120, obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data;

[0064] Step S130: determining the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow velocity of the target station interface.

[0065] According to the method of the present invention, after the operating data of the oil-mixing interface position of the pipeline to be tested is obtained, the target inter-station interface reduced flow velocity corresponding to the pipeline to be tested is determined by using the pre-trained inter-station interface reduced flow velocity determination model. Since the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data, it can truly reflect the inter-station interface reduced flow velocity. Therefore, the target inter-station interface reduced flow velocity determined by the inter-station interface reduced flow velocity determination model is more accurate. Furthermore, based on the target inter-station interface reduced flow velocity, the position of the oil-mixing interface to be tested corresponding to the pipeline to be tested is more accurately determined.

[0066] The solution of the present invention is further described below with reference to the following specific embodiment. In this embodiment, the method for tracking the position of the oil-mixing interface may include the following steps:

[0067] Step S110, obtaining the oil-mixing interface position operating data of the pipeline to be tested, wherein the oil-mixing interface position operating data includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section;

[0068] The oil-mixing interface position operation data is data reflecting the operation of the oil-mixing interface in the pipeline to be tested, which may include but is not limited to the pipe flow rate, the density of the preceding oil product, the density of the succeeding oil product, the starting temperature of the pipe section, and the end temperature of the pipe section. The pipe flow rate refers to the transportation speed of the oil product in the pipeline between adjacent stations; the density of the preceding oil product refers to the density value of the oil product in the preceding batch sequence, and the unit is kg / m 3 The density of the last oil product refers to the density of the oil product in the last batch, and the unit is kg / m 3 The starting temperature of the pipe section refers to the time-averaged temperature at the outlet of the first end of the pipe section obtained by measuring with the temperature sensor, and the unit is degrees Celsius. The ending temperature of the pipe section refers to the time-averaged temperature at the inlet of the end of the pipe section obtained by measuring with the temperature sensor, and the unit is degrees Celsius.

[0069] Step S120, obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data.

[0070] Optionally, the pipeline to be tested includes multiple flow platforms, and the inter-station interface reduced flow velocity corresponding to each flow platform may be different. In the above step S120, the target inter-station interface reduced flow velocity corresponding to the pipeline to be tested is obtained by determining a model based on the operating data of the mixed oil interface position and the pre-trained inter-station interface reduced flow velocity, including:

[0071] A model is determined based on the operating data of the oil-mixing interface position and pre-trained inter-station interface converted flow rates to obtain a target inter-station interface converted flow rate corresponding to a target flow platform at the oil-mixing interface to be measured corresponding to the pipeline to be measured, wherein the plurality of flow platforms include the target flow platform, and the target flow platform is the flow platform currently passed by the oil-mixing interface to be measured.

[0072] Optionally, the above-mentioned inter-station interface reduced flow velocity determination model is trained in the following way:

[0073] A training sample is obtained, where the training sample includes a plurality of sample data corresponding to a sample pipeline, the plurality of sample data being data corresponding to the sample pipeline at different flow platform periods. The training sample includes historical operating data of the oil-mixing interface position of the sample pipeline. For each of the sample data, the sample data includes a pipeline flow rate, a forward oil product density, a backward oil product density, a pipe section starting point temperature, and a pipe section ending point temperature. Each of the sample data corresponds to a real inter-station interface converted flow rate. The pipeline flow rate is equal to the pipe section flow rate multiplied by the pipe section cross-sectional area.

[0074] The initial model is trained according to the training samples to obtain the predicted inter-station interface converted flow velocity corresponding to each sample data;

[0075] Determining the objective function of the initial model according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data;

[0076] If the objective function meets the preset training end condition, the initial model when the training end condition is met will be used as the inter-station interface converted flow velocity determination model; if the objective function does not meet the preset training end condition, the model parameters of the initial model will be adjusted, and the initial model will be retrained according to the adjusted model parameters until the objective function meets the preset training end condition.

[0077] The plurality of sample data are determined based on historical oil-mixed interface position operation data of the sample pipeline.

[0078] During the model training process, if the sample pipeline includes multiple flow platforms, the method further includes: for each sample data, obtaining the actual flow platform-reduced flow velocity corresponding to the 50% concentration interface passing through each flow platform. When a batch of oil is transported within a pipeline, the oil flow velocity undergoes periodic variations due to distribution or unloading, forming multiple flow platforms with varying flow velocities. That is, during transportation, the oil flow velocity undergoes periodic variations, which can affect the location of the oil-mixing interface in the pipeline. Therefore, during the model training process, i.e., training the initial model based on the training samples to obtain the predicted inter-station interface-reduced flow velocity corresponding to each sample data, the method further includes: training the initial model based on the training samples to obtain the predicted flow platform-reduced flow velocity corresponding to each flow platform in each sample data passing through. Training the model based on the actual flow platform-reduced flow velocity corresponding to each different flow platform allows the location of the oil-mixing interface to be determined according to the flow platform-reduced flow velocity corresponding to each flow platform in actual applications, thereby making the determination of the location of the oil-mixing interface more accurate.

[0079] Based on the above processing, the objective function of the initial model is determined according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data, including: for each of the sample data, the initial objective function of the initial model is determined according to the actual flow platform converted flow velocity and the predicted flow platform converted flow velocity corresponding to the sample data; the objective function of the initial model is determined according to the initial loss value corresponding to each of the sample data.

[0080] Optionally, for each sample data, obtaining the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform includes:

[0081] S11, obtaining the instantaneous flow Q corresponding to the 50% concentration interface in the sample pipeline i (T), the total time length TA of the 50% concentration interface passing through the sample pipeline, and the starting time T corresponding to the 50% concentration interface passing through each flow platform i-1 and end time T i ;

[0082] S12, determining a second average flow rate at which a 50% concentration interface passes through the sample pipe within the total time according to the instantaneous flow rate and the total time length One possible implementation method is: according to the instantaneous flow rate and the total time length, the second average flow rate of the 50% concentration interface passing through the sample pipe within the total time length is determined by the first formula and the second formula. Among them, the first formula is:

[0083]

[0084] Among them, T A is the total time length of the 50% concentration interface passing through the sample pipe, in seconds; The average value of the flow meter monitoring data in the time period from 0 to TA, that is, the second average flow rate, in m 3 / s;Q i (T) is the instantaneous flow rate monitored by the SCADA system flowmeter, i.e., the instantaneous flow rate corresponding to the 50% concentration interface in the sample pipe, in m 3 / s;

[0085] S13, for each of the traffic platforms, determine the first average traffic corresponding to the traffic platform according to the total time length, the instantaneous traffic, the start time and end time corresponding to the traffic platform One possible implementation method is to determine the first average flow corresponding to the flow platform by a second formula based on the total time length, the instantaneous flow, the start time and the end time corresponding to the flow platform, wherein the second formula is:

[0086]

[0087] Among them, T i-1 is the starting time of the ith traffic platform period, in seconds; T i is the end time of the ith traffic platform period, in seconds; is the average flow rate during the i-th flow platform period, that is, the first average flow rate, in m 3 / s.

[0088] S14, for each of the flow platforms, convert the flow rate according to the real station interface corresponding to the sample data The first average flow corresponding to the flow platform and the second average flow Determine the actual flow platform conversion flow rate corresponding to each flow platform at a 50% concentration interface

[0089] Optionally, for each sample data, the actual station interface converted flow velocity corresponding to the sample data It is determined by:

[0090] S21, obtaining the length L of the sample channel, the first time when the 50% concentration interface passes through the starting point of the sample channel, and the second time T when the 50% concentration interface passes through the end point of the sample channel z | c＝50％; The first time and the second time can be determined by the following methods:

[0091] For a certain section of pipeline between two adjacent stations, the density variation curve recorded by the upstream station densitometer and the density variation curve recorded by the downstream station densitometer are converted into concentration variation curves respectively, which are specifically determined by the following third formula, where the third formula is:

[0092]

[0093] Among them, C h is the concentration of the downstream oil at the density sensor position at any time, dimensionless; C q is the concentration of the oil product at the density sensor at any time, dimensionless; ρ q The density of the oil in front, in kg / m 3 ρ M The density measured by the density sensor at any time, in kg / m 3 ρ h The density of the downstream oil, in kg / m 3 .

[0094] According to the time-varying curves of the mixed oil concentration at the pipeline starting point station and the time-varying curves of the mixed oil concentration at the end point station, the first time (the moment when the 50% concentration interface passes through the density sensor at the upstream station of the pipeline) and the second time (the moment when the 50% concentration interface passes through the density sensor at the downstream station of the pipeline) can be obtained respectively.

[0095] S22, according to the pipeline length L, the first time T q | c＝50％ and the second time T z | c＝50％ , determine the first converted flow rate corresponding to the 50% concentration interface The first converted flow rate is used as the actual inter-station interface converted flow rate corresponding to the sample data. One possible implementation of step S22 is: according to the pipeline length L, the first time T q | c＝50％ and the second time T z | c＝50％ The first converted flow rate corresponding to the 50% concentration interface is determined by the fourth formula The first converted flow rate is used as the actual inter-station interface converted flow rate corresponding to the sample data. Among them, the fourth formula is:

[0096]

[0097] After determining the actual interface velocity between stations Afterwards, the above S14 specifically includes:

[0098] For each of the flow platforms, the flow rate is converted based on the real station interface corresponding to the sample data. The first average flow corresponding to the flow platform and the second average flow The fifth formula is used to determine the actual flow platform conversion flow rate corresponding to each flow platform at a 50% concentration interface. Among them, the fifth formula is:

[0099]

[0100] After determining the 50% concentration interface, the actual flow platform corresponding to each flow platform is converted into a flow rate. After that, define the following parameters:

[0101] Define the first average flow The average temperature K1 of the starting point temperature of the pipe section within each flow platform period (a period of time) is defined as x1, the average temperature K2 of the end point temperature of the pipe section within each flow platform period (a period of time) is defined as x3, the average value ρ1 of the density of the forward oil product within a period of time is defined as x4, the average value ρ2 of the density of the backward oil product within a period of time is defined as x5, and the 50% concentration interface passing through the real flow platform corresponding to each flow platform is converted into a flow rate Defined as y.

[0102] Define sample variables x i is the input variable with a dimension of 5; i is the output variable with a dimension of 1. According to the above parameters (each sample data corresponds to the above parameters), the mean matrix corresponding to the sample data is determined and the covariance matrix include and include and and They represent the mean matrices of the input variable x, output variable y, and sample variable t in the k-th Gaussian distribution respectively; and They represent the covariance matrix of the input variable x, output variable y and sample variable t in the kth Gaussian distribution. and are transposed matrices of each other, where the mean matrix and the covariance matrix They are expressed by the following sixth and seventh formulas respectively.

[0103]

[0104]

[0105] In the present application, the initial model can be a Gaussian mixture regression model. Before training, the model parameters of the Gaussian mixture regression model can be initialized, including the number of Gaussian distributions K, the weight of the kth Gaussian distribution π k , mean matrix and the covariance matrix The number K of Gaussian distributions can be set manually, and the initialization methods of the remaining parameters can refer to the following eighth to tenth formulas.

[0106]

[0107]

[0108]

[0109] Among them, N is the amount of historical data, that is, the number of sample data.

[0110] After defining the above parameters, for each sample data, the initial loss value corresponding to the sample data is determined by the following method:

[0111] For each of the sample data, based on the sample data and the reduced flow rates of each real flow platform corresponding to the sample data, determine a mean matrix and a covariance matrix corresponding to the sample data, wherein the mean matrix represents the relationship between the mean corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the mean corresponding to each historical oil-mixing interface position operating data in the sample data, and the covariance matrix represents the relationship between the covariance corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the covariance corresponding to each historical oil-mixing interface position operating data in the sample data;

[0112] For each sample data, an initial objective function corresponding to the sample data is calculated using a likelihood function according to the mean matrix and the covariance matrix.

[0113] The above-mentioned step of calculating the initial objective function corresponding to each sample data by using the likelihood function according to the mean matrix and the covariance matrix may specifically include:

[0114] Calculate sample t i The posterior probability of belonging to the kth Gaussian distribution is the Gaussian distribution probability density function. Among them, the posterior probability It can be determined by the eleventh formula:

[0115]

[0116] According to the following formulas 12 to 14, the parameters of the k-th Gaussian distribution are estimated respectively, including π k 、 and Among them, the twelfth to fourteenth formulas are respectively:

[0117]

[0118]

[0119]

[0120] Repeat the above steps, i.e., formulas (12) to (14), and calculate the likelihood function according to the fifteenth formula (Θ) (The change of the objective function corresponding to the initial model. When the stop condition (training end condition) corresponding to the sixteenth formula is met, the iteration process is completed and the model parameters are saved. Where Θ(n) represents the calculated value of the likelihood function at the nth iteration, ∈ is the error threshold, which is generally 10 -10 Among them, the fifteenth and sixteenth formulas are:

[0121]

[0122]

[0123] In the solution of the present application, the initial model is trained based on the training samples described above to obtain the predicted flow platform converted flow rate corresponding to each flow platform in each sample data at a 50% concentration interface, including:

[0124] Calculate the sample estimate (sample data) to be predicted according to the seventeenth formula t q The posterior probability of belonging to the kth Gaussian distribution And according to the eighteenth formula, determine y q The estimated results That is, the predicted flow platform converted flow rate. It should be noted that during the model training process, the output of the model is the predicted flow platform converted flow rate. In actual use, the output of the model is the target flow platform converted flow rate, that is, is the target flow platform converted flow rate. Among them, yq is the true value of y corresponding to the sample to be predicted, that is, the actual flow platform converted flow rate.

[0125]

[0126]

[0127] After determining the predicted flow platform corresponding to each sample data, the flow rate is converted Afterwards, the starting time T corresponding to the target flow platform can be calculated by combining the oil mixing interface corresponding to the sample data. q-1 and end time T q , the position of the oil-mixing interface is determined by the nineteenth formula, where the nineteenth formula is:

[0128]

[0129] Where l(t) is the distance from the origin of the Lagrangian coordinate system corresponding to the oil-mixing interface (i.e., the location of the oil-mixing interface) to the starting end of the pipe section, in meters, and Q is the number of flow platforms.

[0130] Step S130: determining the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow velocity of the target station interface.

[0131] The position of the measured mixed oil interface is affected not only by the target station interface converted flow rate, but also by the start time and end time corresponding to the measured mixed oil interface passing through the target flow platform. Therefore, step S130 specifically includes: obtaining the start time and end time corresponding to the measured mixed oil interface passing through the target flow platform; and determining the position of the measured mixed oil interface corresponding to the pipeline under test based on the target station interface converted flow rate corresponding to the target flow platform of the measured mixed oil interface and the start time and end time corresponding to the measured mixed oil interface.

[0132] In order to better illustrate and understand the principle of the method provided by the present invention, the solution of the present invention is described below in conjunction with an optional specific embodiment. It should be noted that the specific implementation of each step in this specific embodiment should not be understood as limiting the solution of the present invention. On the basis of the principle of the solution provided by the present invention, other implementations that can be thought of by those skilled in the art should also be considered as within the scope of protection of the present invention.

[0133] Based on Figure 1 Based on the same principle as the method shown in , the embodiment of the present invention further provides an adaptive oil-mixing interface position tracking device 20, such as Figure 2 As shown in , the oil-mixing interface position tracking device 20 may include a data acquisition module 210, a target station interface reduced flow rate determination module 220, and an oil-mixing interface position determination module 230, wherein:

[0134] The data acquisition module 210 is used to obtain the oil-mixing interface position operating data of the pipeline to be tested, wherein the oil-mixing interface position operating data includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section;

[0135] a target inter-station interface reduced flow velocity determination module 220 for obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline under test based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data;

[0136] The oil-mixing interface position determination module 230 is configured to determine the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the target station interface converted flow rate.

[0137] Optionally, the above-mentioned inter-station interface converted flow rate determination model is obtained by training the following training module, wherein the training module is used to obtain training samples, the training samples include multiple sample data corresponding to the sample pipeline, the multiple sample data are data corresponding to the sample pipeline at different flow platform time periods, the training samples include historical mixed oil interface position operation data of the sample pipeline, for each of the sample data, the sample data includes pipeline flow rate, forward oil product density, backward oil product density, pipe section starting point temperature and pipe section end point temperature, each of the sample data corresponds to a real inter-station interface converted flow rate;

[0138] The initial model is trained according to the training samples to obtain the predicted inter-station interface converted flow velocity corresponding to each sample data;

[0139] Determining the objective function of the initial model according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data;

[0140] If the objective function meets the preset training end condition, the initial model when the training end condition is met will be used as the inter-station interface converted flow velocity determination model; if the objective function does not meet the preset training end condition, the model parameters of the initial model will be adjusted, and the initial model will be retrained according to the adjusted model parameters until the objective function meets the preset training end condition.

[0141] Optionally, the sample pipeline includes multiple flow platforms, and the device further includes:

[0142] A flow platform converted flow rate determination module is used to obtain, for each sample data, a real flow platform converted flow rate corresponding to a 50% concentration interface passing through each flow platform;

[0143] The training module is specifically used to train the initial model based on the training samples to obtain the predicted station-to-station interface converted flow velocity corresponding to each sample data:

[0144] The initial model is trained according to the training samples to obtain the predicted flow platform converted flow velocity corresponding to each flow platform in each sample data when the 50% concentration interface passes through the sample data;

[0145] The training module is specifically used to determine the objective function of the initial model based on the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data:

[0146] For each of the sample data, the initial loss value of the initial model is determined based on the converted flow rates of each real traffic platform and each predicted traffic platform corresponding to the sample data; and the objective function of the initial model is determined based on the initial loss values ​​corresponding to each of the sample data.

[0147] Optionally, for each sample data, when obtaining the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform, the training module is specifically used to:

[0148] Obtain the instantaneous flow corresponding to the 50% concentration interface in the sample pipeline, the total time length of the 50% concentration interface passing through the sample pipeline, and the start time and end time corresponding to the 50% concentration interface passing through each of the flow platforms; for each of the flow platforms, determine the first average flow corresponding to the flow platform based on the total time length, the instantaneous flow, and the start time and end time corresponding to the flow platform; determine the second average flow through the sample pipeline within the total time length based on the instantaneous flow and the total time length; for each of the flow platforms, determine the real flow platform converted flow rate corresponding to the 50% concentration interface passing through each of the flow platforms based on the real inter-station interface converted flow rate corresponding to the sample data, the first average flow rate and the second average flow rate corresponding to the flow platform.

[0149] Optional. For each sample data, the actual station interface converted velocity corresponding to the sample data is determined by the following method:

[0150] Obtain the pipeline length of the sample pipeline, the first time when the 50% concentration interface passes through the starting point of the sample pipeline, and the second time when the 50% concentration interface passes through the end point of the sample pipeline; determine the first converted flow rate corresponding to the 50% concentration interface based on the pipeline length, the first time, and the second time, and use the first converted flow rate as the actual inter-station interface converted flow rate corresponding to the sample data.

[0151] Optionally, the pipeline to be tested includes multiple flow platforms. When the training module determines a model based on the operating data of the oil-mixing interface position and the pre-trained inter-station interface reduced flow rate to obtain the target inter-station interface reduced flow rate corresponding to the pipeline to be tested, it is specifically used to:

[0152] A model is determined based on the operating data of the oil-mixing interface position and a pre-trained inter-station interface reduced flow rate, to obtain a target inter-station interface reduced flow rate corresponding to a target flow platform of the oil-mixing interface to be tested corresponding to the pipeline to be tested, wherein the plurality of flow platforms include the target flow platform, and the target flow platform is the flow platform currently passed by the oil-mixing interface to be tested;

[0153] The above-mentioned oil-mixing interface position determination module is specifically used to determine the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the interface converted flow rate between the target stations:

[0154] Obtain the start time and end time corresponding to the measured mixed oil interface passing through the target flow platform; determine the position of the measured mixed oil interface corresponding to the pipeline to be tested according to the converted flow velocity of the target station interface corresponding to the measured mixed oil interface at the target flow platform and the start time and end time corresponding to the measured mixed oil interface.

[0155] Optionally, for each sample data, the initial loss value corresponding to the sample data is determined by:

[0156] For each of the sample data, the mean matrix and covariance matrix corresponding to the sample data are determined based on the sample data and the converted flow rates of each real flow platform corresponding to the sample data. The mean matrix represents the relationship between the mean corresponding to the converted flow rates of each real flow platform corresponding to the sample data and the mean corresponding to each historical oil mixing interface position operating data in the sample data. The covariance matrix represents the relationship between the covariance corresponding to the converted flow rates of each real flow platform corresponding to the sample data and the covariance corresponding to each historical oil mixing interface position operating data in the sample data. For each of the sample data, the initial loss value corresponding to the sample data is calculated by the likelihood function based on the mean matrix and the covariance matrix.

[0157] The oil-mixing interface position tracking device of the embodiment of the present invention can execute the oil-mixing interface position tracking method provided by the embodiment of the present invention, and its implementation principle is similar. The actions performed by each module and unit in the oil-mixing interface position tracking device in each embodiment of the present invention correspond to the steps in the oil-mixing interface position tracking method in each embodiment of the present invention. For the detailed functional description of each module of the oil-mixing interface position tracking device, please refer to the description of the corresponding oil-mixing interface position tracking method shown in the previous text, and will not be repeated here.

[0158] Among them, the above-mentioned oil-mixing interface position tracking device can be a computer program (including program code) running in a computer device, for example, the oil-mixing interface position tracking device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present invention.

[0159] In some embodiments, the oil-mixing interface position tracking device provided in the embodiments of the present invention can be implemented by a combination of software and hardware. As an example, the oil-mixing interface position tracking device provided in the embodiments of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the oil-mixing interface position tracking method provided in the embodiments of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0160] In other embodiments, the oil-mixing interface position tracking device provided by the embodiments of the present invention can be implemented in a software manner. Figure 2 A device for tracking the position of a mixed oil interface stored in a memory is shown. The device can be software in the form of a program or plug-in, and includes a series of modules, including a data acquisition module 210, a target station interface reduced flow rate determination module 220, and a mixed oil interface position determination module 230, for implementing the mixed oil interface position tracking method provided in an embodiment of the present invention.

[0161] The modules involved in the embodiments of the present invention may be implemented in software or hardware, wherein the name of a module does not necessarily limit the module itself.

[0162] Based on the same principle as the method shown in the embodiments of the present invention, an electronic device is also provided in the embodiments of the present invention, which may include but is not limited to: a processor and a memory; the memory is used to store computer programs; the processor is used to execute the method shown in any embodiment of the present invention by calling the computer program.

[0163] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0164] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 4001 may 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, and the like.

[0165] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0166] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, 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 to these.

[0167] The memory 4003 is used to store application code (computer program) for executing the solution of the present invention, and is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0168] Among them, the electronic device can also be a terminal device, Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0169] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0170] According to another aspect of the present invention, a computer program product or computer program is provided. The computer program product or computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method for tracking the position of the oil-contaminated interface provided in the various implementations described above.

[0171] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0172] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0173] The computer-readable storage medium provided by the embodiments of the present invention may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.

[0174] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0175] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present invention.

Claims

1. A method for tracking the position of an oil-mixing interface, characterized in that: include: Obtaining the oil-mixing interface position operating data of the pipeline to be tested, wherein the oil-mixing interface position operating data includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section; Obtaining a target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data; Determining the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow velocity of the target station interface; The pipeline to be tested includes multiple flow platforms, and the model is determined based on the operating data of the oil-mixing interface position and the pre-trained inter-station interface reduced flow rate to obtain the target inter-station interface reduced flow rate corresponding to the pipeline to be tested, including: A target inter-station interface reduced flow rate corresponding to the target flow platform at the target inter-station interface of the tested pipeline corresponding to the tested oil mixed interface is obtained by determining a model based on the oil mixed interface position operation data and a pre-trained inter-station interface reduced flow rate. The plurality of flow platforms include the target flow platform, which is the flow platform currently passed by the oil-mixing interface to be measured; and determining the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow velocity of the target inter-station interface, including: Obtaining the start time and end time corresponding to the oil mixture interface to be tested passing through the target flow platform; The position of the tested oil mixed interface corresponding to the tested pipeline is determined according to the target station interface converted flow rate corresponding to the tested oil mixed interface at the target flow platform, the start time and the end time corresponding to the tested oil mixed interface.

2. The method according to claim 1, characterized in that The inter-station interface reduced velocity determination model is trained in the following way: Acquire a training sample, the training sample including a plurality of sample data corresponding to a sample pipeline, the plurality of sample data being data corresponding to the sample pipeline at different flow platform periods, the training sample including historical oil-mixing interface position operation data of the sample pipeline, each of the sample data including pipeline flow rate, forward oil product density, backward oil product density, pipe section starting point temperature, and pipe section ending point temperature, each of the sample data corresponding to a real inter-station interface converted flow rate; The initial model is trained according to the training samples to obtain the predicted inter-station interface converted flow velocity corresponding to each sample data; Determining the objective function of the initial model according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data; If the objective function meets the preset training end condition, the initial model when the training end condition is met will be used as the inter-station interface converted flow velocity determination model; if the objective function does not meet the preset training end condition, the model parameters of the initial model will be adjusted, and the initial model will be retrained according to the adjusted model parameters until the objective function meets the preset training end condition.

3. The method according to claim 2, characterized in that The sample pipeline includes a plurality of flow platforms, and the method further includes: For each sample data, obtaining the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform; The initial model is trained based on the training samples to obtain the predicted station-to-station interface converted flow velocity corresponding to each sample data, including: The initial model is trained according to the training samples to obtain the predicted flow platform converted flow velocity corresponding to each flow platform in each sample data when the 50% concentration interface passes through the sample data; Determining the total objective function value of the initial model according to the actual inter-station interface converted flow velocity and the predicted inter-station interface converted flow velocity corresponding to each of the sample data includes: For each sample data, determining the initial loss value of the initial model according to the converted flow rates of each real flow platform and the converted flow rates of each predicted flow platform corresponding to the sample data; The objective function of the initial model is determined according to the initial loss values ​​corresponding to the sample data.

4. The method according to claim 3, characterized in that For each sample data, obtaining the actual flow platform converted flow rate corresponding to the 50% concentration interface passing through each flow platform includes: Obtaining the instantaneous flow rate corresponding to the 50% concentration interface in the sample pipeline, the total length of time the 50% concentration interface passes through the sample pipeline, and the start and end times corresponding to the 50% concentration interface passing through each flow platform; For each of the traffic platforms, determining a first average traffic corresponding to the traffic platform according to the total time length, the instantaneous traffic, and the start time and end time corresponding to the traffic platform; Determining a second average flow rate at which a 50% concentration interface passes through the sample pipe within the total time period based on the instantaneous flow rate and the total time period; For each of the flow platforms, the real flow platform converted flow rate corresponding to the 50% concentration interface passing through each of the flow platforms is determined based on the real inter-station interface converted flow rate corresponding to the sample data, the first average flow rate and the second average flow rate corresponding to the flow platform.

5. The method according to claim 2, characterized in that For each sample data, the actual inter-station interface converted velocity corresponding to the sample data is determined by the following method: Acquiring the length of the sample channel, a first time when a 50% concentration interface passes through a starting point of the sample channel, and a second time when a 50% concentration interface passes through an end point of the sample channel; A first converted flow rate corresponding to a 50% concentration interface is determined according to the pipeline length, the first time, and the second time, and the first converted flow rate is used as the actual inter-station interface converted flow rate corresponding to the sample data.

6. The method according to claim 3, characterized in that For each sample data, the initial loss value corresponding to the sample data is determined in the following manner: For each of the sample data, based on the sample data and the reduced flow rates of each real flow platform corresponding to the sample data, determine a mean matrix and a covariance matrix corresponding to the sample data, wherein the mean matrix represents the relationship between the mean corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the mean corresponding to each historical oil-mixing interface position operating data in the sample data, and the covariance matrix represents the relationship between the covariance corresponding to the reduced flow rates of each real flow platform corresponding to the sample data and the covariance corresponding to each historical oil-mixing interface position operating data in the sample data; For each sample data, an initial objective function corresponding to the sample data is calculated using a likelihood function according to the mean matrix and the covariance matrix.

7. A device for tracking the position of an oil-mixing interface, characterized in that: The method for tracking the position of an oil-mixing interface according to claim 1 is adopted, wherein the device comprises: A data acquisition module is used to obtain the operating data of the oil-mixing interface position of the pipeline to be tested, wherein the operating data of the oil-mixing interface position includes the flow rate of the pipeline section, the density of the upstream oil product, the density of the downstream oil product, the starting temperature of the pipeline section, and the ending temperature of the pipeline section; a target inter-station interface reduced flow velocity determination module, configured to obtain the target inter-station interface reduced flow velocity corresponding to the pipeline to be tested based on the oil-mixing interface position operating data and a pre-trained inter-station interface reduced flow velocity determination model, wherein the inter-station interface reduced flow velocity determination model is trained based on historical oil-mixing interface position operating data; The oil-mixing interface position determination module is used to determine the position of the oil-mixing interface to be measured corresponding to the pipeline to be measured according to the converted flow rate of the target station interface.

8. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images