Easily-coagulated wax-containing crude oil pipeline conveying control system and method

Abstract

The invention provides an easily-coagulated wax-containing crude oil pipeline conveying control system and method. The method comprises the steps that viscosity data of easily-coagulated wax-containing crude oil at a detection point in the conveying process and parameter data of all working conditions are collected; determining an abnormal point of each working condition parameter data according to the viscosity data, screening out a plurality of effective data from the corresponding working condition parameter data through each abnormal point, and determining redundancy deviation according to all the effective data; and performing optimization on each working condition parameter based on the redundancy deviation to obtain the sensitivity of the change of the viscosity of the easily-coagulated wax-bearing crude oil to the data change under different working condition parameters, and determining a predicted value of the viscosity of the easily-coagulated wax-bearing crude oil according to all the sensitivity. And controlling the output power of the pour point depressing device in the conveying process of the easily-coagulated wax-containing crude oil pipeline according to the predicted value. By adopting the scheme of the invention, the proper working condition parameters can be selected to predict the viscosity of the crude oil, so that the extra consumption in the crude oil transportation operation is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of crude oil transportation, and more specifically, to a control system and method for pipeline transportation of easily condensable waxy crude oil. Background Art

[0002] Crude oil transportation technology is an important part of the petroleum industry, involving the transportation of extracted crude oil from oil fields to refineries or other processing facilities. Among them, crude oil pipeline transportation is an efficient and economical way to transport crude oil over long distances and is widely used in the petroleum industry.

[0003] Most of the crude oil in my country is waxy crude oil that is easy to condense. This type of crude oil contains a high amount of paraffin, which is easy to crystallize or solidify at low temperatures, resulting in increased viscosity and even clogging of pipelines. Therefore, during transportation, it is necessary to reduce the viscosity of waxy crude oil by technical means to avoid clogging of the transportation pipeline. In the prior art, there are already a variety of methods to predict the viscosity of waxy crude oil that is easy to condense during transportation and adjust the decondensation strategy. However, in actual applications, the crude oil transported is often a complex mixture of multiple crude oils, depressants and water. The rheological properties of this mixture are very complex. For example, at low temperatures, the mixture exhibits the properties of a non-Newtonian fluid. At this time, the viscosity of the mixture is related to the shear rate of the mixture, and when the temperature rises, the mixture exhibits the properties of a Newtonian fluid. At this time, the viscosity of the mixture is independent of the shear rate of the mixture. This leads to the fact that when the rheological properties of the transported crude oil are unknown, the use of previous methods to predict the viscosity of easily condensed waxy crude oil is prone to introduce irrelevant parameters or omission of relevant parameters, resulting in errors in the viscosity prediction results of easily condensed waxy crude oil, which in turn causes unnecessary additional consumption in crude oil transportation operations. Therefore, how to select suitable operating parameters to predict crude oil viscosity and thereby reduce additional consumption in crude oil transportation operations has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a control system and method for pipeline transportation of easily condensable waxy crude oil, which can select suitable operating parameters to predict the viscosity of crude oil, thereby reducing additional consumption in crude oil transportation operations.

[0005] In a first aspect, the present application provides a method for controlling pipeline transportation of easily condensable waxy crude oil, comprising:

[0006] Preset detection points on the condensable waxy crude oil pipeline, and collect viscosity data and various operating parameter data of the condensable waxy crude oil at the detection points during transportation;

[0007] Determine the abnormal point of each operating parameter data according to the viscosity data, screen out multiple valid data of the easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determine the redundant deviation of all operating parameter data according to all the valid data;

[0008] Based on the redundant deviation, each operating parameter is optimized to obtain the sensitivity of the viscosity of the easily condensable waxy crude oil to the data change under different operating parameters, and a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment is constructed according to all the sensitivities;

[0009] Obtain various transportation parameters of the easily condensable waxy crude oil at the current moment, input all the transportation parameters into the rheological-viscosity prediction model, obtain the predicted value of the viscosity of the easily condensable waxy crude oil, and control the output power of the pour point depressant during the pipeline transportation of the easily condensable waxy crude oil according to the predicted value

[0010] In some embodiments, determining the abnormal point of each operating parameter data according to the viscosity data specifically includes:

[0011] Selecting a working condition parameter data as selected working condition parameter data;

[0012] Converting the selected operating condition parameter data into a selected operating condition sequence;

[0013] Converting the viscosity data into a viscosity sequence;

[0014] Determining the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods;

[0015] Determine the abnormal point of the selected operating condition parameter data according to all the correlation degrees;

[0016] Continue to determine the abnormal points of the remaining parameter data for each operating condition.

[0017] In some embodiments, determining the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods specifically includes:

[0018] A comparison window is preset, and an operating condition subsequence and a viscosity subsequence within the same period are extracted from the selected operating condition sequence and the viscosity sequence through the comparison window;

[0019] Determining the correlation between the operating condition subsequence and the viscosity subsequence;

[0020] The operating condition subsequences and viscosity subsequences in other time periods are continuously intercepted from the selected operating condition sequence and the viscosity sequence through the comparison window until the number of interceptions reaches a preset cutoff threshold, thereby obtaining the correlations in multiple time periods.

[0021] In some embodiments, determining the redundant deviation of all operating parameter data according to all valid data specifically includes:

[0022] Standardize all valid data to obtain standardized data corresponding to each valid data;

[0023] Determine the sensitivity of the change in viscosity of waxy crude oil to each operating parameter;

[0024] Determine the prediction error based on all the standardized data and all the sensitivities to be determined;

[0025] Determine first-order regularization constraints for all pending sensitivities;

[0026] The redundant deviation of all operating condition parameter data is determined according to the prediction error and the first-order regularization constraint.

[0027] In some embodiments, constructing a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment based on all sensitivities specifically includes:

[0028] Extract multiple effective parameters from all operating parameters according to all sensitivities;

[0029] The rheological-viscosity prediction model of the condensable waxy crude oil at the current moment is constructed based on all effective parameters.

[0030] In some embodiments, controlling the output power of the pour point depressant during pipeline transportation of the condensable waxy crude oil according to the predicted value specifically includes:

[0031] When the predicted value exceeds a preset viscosity threshold, increasing the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil;

[0032] When the predicted value does not exceed the preset viscosity threshold, the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil is not adjusted.

[0033] In some embodiments, the condensation reduction device includes: a heating device, an ultrasonic viscosity reduction device and an electromagnetic viscosity reduction device.

[0034] In a second aspect, the present application provides a pipeline transportation control system for easily condensable waxy crude oil, the pipeline transportation control system for easily condensable waxy crude oil includes a power control unit, the power control unit includes:

[0035] A collection module is used to preset a detection point on the easily condensable waxy crude oil pipeline and collect viscosity data and various operating condition parameter data of the easily condensable waxy crude oil at the detection point during transportation;

[0036] A processing module, used to determine the abnormal point of each operating parameter data according to the viscosity data, screen out multiple valid data of the easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determine the redundant deviation of all operating parameter data according to all the valid data;

[0037] The processing module is also used to optimize various operating parameters based on the redundant deviation, thereby obtaining the sensitivity of the viscosity of the easily condensable waxy crude oil to the data changes under different operating parameters, and constructing a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment according to all the sensitivities;

[0038] The execution module is used to obtain various transportation parameters of the easily condensable waxy crude oil at the current moment, input all the transportation parameters into the rheology-viscosity prediction model, obtain the predicted value of the viscosity of the easily condensable waxy crude oil, and control the output power of the decondensation device during the pipeline transportation of the easily condensable waxy crude oil according to the predicted value.

[0039] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned pipeline transportation control method for easily condensable waxy crude oil.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned pipeline transportation control method for easily condensable waxy crude oil.

[0041] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0042] In the control system and method for pipeline transportation of condensable waxy crude oil provided by the present application, first, by presetting detection points on the pipeline of condensable waxy crude oil, and collecting viscosity data and various operating parameter data of the condensable waxy crude oil at the detection points during transportation; determining the abnormal points of each operating parameter data according to the viscosity data, screening multiple valid data of the condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determining the redundant deviation of all operating parameter data according to all valid data; optimizing each operating parameter based on the redundant deviation, and then obtaining the sensitivity of the viscosity of the condensable waxy crude oil to the data change under different operating parameters, and constructing a rheological-viscosity prediction model of the condensable waxy crude oil at the current moment according to all sensitivities; obtaining various transportation parameters of the condensable waxy crude oil at the current moment, inputting all transportation parameters into the rheological-viscosity prediction model, obtaining the predicted value of the viscosity of the condensable waxy crude oil, and controlling the output power of the pour point reduction device during the pipeline transportation of the condensable waxy crude oil according to the predicted value.

[0043] It can be seen that the present application extracts the abnormal points of the response of the change of viscosity of the easily condensable waxy crude oil to each operating parameter data, screens out the operating parameter data in the same rheological state (i.e., valid data), and evaluates how much redundant deviation will be generated when the viscosity of the easily condensable waxy crude oil is predicted directly through all valid data. Subsequently, the influence of each operating parameter on the viscosity of the easily condensable waxy crude oil is adaptively adjusted (i.e., each operating parameter is optimized based on the redundant deviation) to obtain the sensitivity of the change of viscosity of the easily condensable waxy crude oil to the response of each operating parameter. Subsequently, a rheological-viscosity prediction model is constructed based on all sensitivities, and the output power of the decondensation device during the pipeline transportation of the easily condensable waxy crude oil is controlled according to the prediction results of the rheological-viscosity prediction model to avoid the incorrect working power of the decondensation device due to prediction errors. In summary, the present application can select suitable operating parameters to predict the viscosity of crude oil, thereby reducing the additional consumption in the crude oil transportation operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is an exemplary flow chart of a method for controlling pipeline transportation of easily condensable waxy crude oil according to some embodiments of the present application;

[0045] Figure 2 It is a structural schematic diagram of a method for controlling pipeline transportation of easily condensable waxy crude oil according to some embodiments of the present application;

[0046] Figure 3 is an exemplary flow chart for determining abnormal points according to some embodiments of the present application;

[0047] Figure 4 is a schematic diagram of the structure of a power control unit according to some embodiments of the present application;

[0048] Figure 5 It is a structural schematic diagram of a computer device for implementing a method for controlling the transportation of easily condensable waxy crude oil through a pipeline according to some embodiments of the present application. DETAILED DESCRIPTION

[0049] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0050] refer to Figure 1 , which is an exemplary flow chart of a pipeline transportation control method for easily condensable waxy crude oil according to some embodiments of the present application. The pipeline transportation control method 100 for easily condensable waxy crude oil mainly includes the following steps:

[0051] In step 101, a detection point is preset on a pipeline of easily condensable waxy crude oil, and viscosity data and various operating parameter data of the easily condensable waxy crude oil at the detection point during transportation are collected.

[0052] It should be noted that the detection points in the present application can be preset according to actual operational requirements. For example, a detection point can be set on a crude oil pipeline one kilometer away from the starting station. Those skilled in the art know that the detection point can be set at other locations on the crude oil pipeline according to actual needs, which falls within the scope of protection of the present invention and will not be repeated here.

[0053] In specific implementation, the viscosity data and various operating parameter data of the easily condensable waxy crude oil at the detection point during the transportation process can be collected in the following manner, namely: the viscosity value and various operating parameter values ​​of the easily condensable waxy crude oil at the detection point can be collected by an intelligent sensor according to a preset sampling interval, and all the collected viscosity values ​​are used as viscosity data, and all the collected operating parameter values ​​of each operating parameter are used as the operating parameter data of the corresponding operating parameter. For example, the sampling interval can be preset to 1 second.

[0054] It should be noted that the intelligent sensor in the present application is an integrated sensor that can collect the viscosity and various operating parameters of the easily condensable waxy crude oil during pipeline transportation, wherein the various operating parameters include the temperature of the crude oil, the temperature in the transportation pipeline, and the shear rate of the crude oil. In other embodiments, the operating parameters may also include other parameters that can affect the viscosity of the crude oil during the crude oil transportation process, which are not limited here.

[0055] In some embodiments, reference Figure 2 , which is a structural schematic diagram of realizing pipeline transportation control of easily condensable waxy crude oil according to some embodiments of the present application, and the structural schematic diagram mainly includes:

[0056] The starting station is responsible for receiving data from the smart sensor and controlling and monitoring the transportation process based on the received data;

[0057] Intelligent sensors are used to collect the viscosity and various operating parameters of waxy crude oil during pipeline transportation, and transmit the collected data to the starting station;

[0058] Crude oil pipelines are used to transport waxy crude oil that is easy to condense;

[0059] The condensate reducing device is used to receive control instructions from the starting station and reduce the condensate of the easily condensable waxy crude oil during transportation according to the control instructions.

[0060] In step 102, the abnormal point of each operating parameter data is determined according to the viscosity data, and multiple valid data of the easily condensable waxy crude oil in the same rheological state are screened out from the corresponding operating parameter data through each abnormal point, and the redundant deviation of all operating parameter data is determined according to all the valid data.

[0061] In some embodiments, reference Figure 3, which is an exemplary flow chart for determining abnormal points according to some embodiments of the present application. In the present application, determining the abnormal points of each operating condition parameter data according to the viscosity data can be implemented by the following steps:

[0062] In step 1021, a working condition parameter data is selected as selected working condition parameter data;

[0063] In step 1022, the selected operating condition parameter data is converted into a selected operating condition sequence;

[0064] In step 1023, the viscosity data is converted into a viscosity sequence;

[0065] In step 1024, the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods is determined;

[0066] In step 1025, the abnormal points of the selected operating condition parameter data are determined according to all the correlation degrees;

[0067] In step 1026 , continue to determine the abnormal points of each remaining operating parameter data.

[0068] In specific implementation, the conversion of the selected operating condition parameter data into the selected operating condition sequence can be achieved in the following manner, that is, all the operating condition parameter values ​​in the selected operating condition parameter data can be sorted in the order of collection, and the sorted sequence is used as the selected operating condition sequence.

[0069] In addition, in a specific implementation, the conversion of the viscosity data into a viscosity sequence may be achieved in the following manner, that is, all viscosities in the viscosity data may be sorted in the order of collection, and the sorted sequence is used as the viscosity sequence.

[0070] In some embodiments, determining the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods may be achieved by using the following steps:

[0071] A comparison window is preset, and an operating condition subsequence and a viscosity subsequence within the same period are extracted from the selected operating condition sequence and the viscosity sequence through the comparison window;

[0072] Determining the correlation between the operating condition subsequence and the viscosity subsequence;

[0073] The operating condition subsequences and viscosity subsequences in other time periods are continuously intercepted from the selected operating condition sequence and the viscosity sequence through the comparison window until the number of interceptions reaches a preset cutoff threshold, thereby obtaining the correlations in multiple time periods.

[0074] It should be noted that, in the present application, the comparison window can be preset according to the length of the viscosity sequence. For example, if the viscosity sequence includes 1000 viscosities, the comparison window can be preset to 10.

[0075] In specific implementation, extracting the operating condition subsequence and viscosity subsequence within the same time period from the selected operating condition sequence and the viscosity sequence through the comparison window can be achieved in the following manner, namely: first, selecting a sequence consisting of the cth to c+nth operating condition parameter values ​​from the selected operating condition sequence as the operating condition subsequence, and then selecting a sequence consisting of the c+1th to c+n+1th viscosity values ​​from the viscosity sequence as the viscosity subsequence, wherein c is any value from 1 to Ln-1, L is the length of the viscosity sequence, and n is the length of the comparison window.

[0076] It should be noted that in the present application, the operating condition subsequence is a sequence composed of operating condition parameter values ​​within a specific period of time, and the viscosity subsequence is a sequence composed of viscosity values ​​within a specific period of time.

[0077] In specific implementation, determining the correlation between the operating condition subsequence and the viscosity subsequence can be achieved in the following manner, namely: first, calculating the average value of the operating condition subsequence and the average value of the viscosity subsequence, then subtracting the average value of the operating condition subsequence from each operating condition parameter value in the operating condition subsequence, and using the obtained sequence as the operating condition deviation sequence, and subtracting the average value of the viscosity subsequence from each viscosity value in the viscosity subsequence, and using the obtained sequence as the viscosity deviation sequence, then, multiplying the operating condition deviation sequence and the viscosity deviation sequence correspondingly and summing them, and using the obtained value as k, then, multiplying the variance of the operating condition subsequence and the variance of the viscosity subsequence and taking the root, multiplying the inverse of the obtained value by k, and finally, using the obtained value as the correlation between the operating condition subsequence and the viscosity subsequence.

[0078] It should be noted that the correlation degree in this application is a parameter indicating the degree of correlation between the change in operating parameters and the change in viscosity within a specific period of time. The larger the absolute value of the correlation degree, the more correlated the change in operating parameters and the change in viscosity within a specific period of time. The smaller the absolute value of the correlation degree, the less correlated the change in operating parameters and the change in viscosity within a specific period of time.

[0079] In addition, it should be noted that the cut-off threshold in the present application can be preset according to the length of the viscosity sequence. For example, the cut-off threshold can be preset to a value obtained by subtracting one from the length of the viscosity sequence.

[0080] Furthermore, it should be noted that the operating condition subsequence and viscosity subsequence intercepted each time in the present application are different sequences. For example, the first time the 1st to 10th operating condition parameter values ​​are intercepted from the operating condition subsequence as the operating condition subsequence, then the subsequent operating condition parameter values ​​are intercepted from the zth to z+9th, and z is not equal to 1.

[0081] In specific implementation, determining the abnormal point of the selected operating condition parameter data according to all the correlations can be achieved in the following manner, namely: first, all the correlations are sorted according to the order of the first viscosity value in the corresponding viscosity subsequence in the viscosity sequence, and then the correlation that is less than a preset correlation threshold for the first time in the arranged sequence is taken as the abnormal correlation, and the sampling moment of the first viscosity value in the viscosity subsequence corresponding to the abnormal correlation is taken as the abnormal point of the response of the change in viscosity of the condensable waxy crude oil to the selected operating condition parameter data.

[0082] It should be noted that the abnormal point in the present application is the time point at which the rheological properties of the condensable waxy crude oil change. The factors affecting the viscosity change of the condensable waxy crude oil change before and after this time point. For example, the viscosity change of the condensable waxy crude oil before this time point is related to the temperature and shear rate in the operating parameters, and the viscosity change of the condensable waxy crude oil after this time point is only related to the temperature and has nothing to do with the shear rate. Then this time point is the abnormal point of the response of the viscosity change of the condensable waxy crude oil to the shear rate.

[0083] In some embodiments, screening out multiple valid data of easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point means taking the operating parameter value of the corresponding abnormal point in each operating parameter data up to the current moment as the valid data of the corresponding operating parameter data.

[0084] It should be noted that the effective data in this application refers to the operating parameter data that can effectively represent the rheological properties of the easily condensable waxy crude oil at the current moment.

[0085] In some embodiments, determining the redundant deviation of all operating condition parameter data according to all valid data may be implemented by the following steps:

[0086] Standardize all valid data to obtain standardized data corresponding to each valid data;

[0087] Determine the sensitivity of the change in viscosity of waxy crude oil to each operating parameter;

[0088] Determine the prediction error based on all the standardized data and all the sensitivities to be determined;

[0089] Determine first-order regularization constraints for all pending sensitivities;

[0090] The redundant deviation of all operating condition parameter data is determined according to the prediction error and the first-order regularization constraint.

[0091] In specific implementation, all valid data are standardized, and the standardized data corresponding to each valid data can be achieved in the following manner, namely: all valid data can be standardized by the mean-maximum value standardization in the prior art, and the standardized data are used as the standardized data of the corresponding valid data.

[0092] It should be noted that the standardized data in this application is valid data after standardization. Since the units of various operating parameters are different, they need to be standardized to the same range before processing.

[0093] In specific implementation, determining the undetermined sensitivity of each operating parameter response to the change in viscosity of the condensable waxy crude oil can be achieved in the following manner, that is, the undetermined sensitivity of each operating parameter response can be preset to one. In other embodiments, the undetermined sensitivity of each operating parameter response can also be preset to other values, which are not limited here.

[0094] It should be noted that the pending sensitivity in this application is a sensitivity that has not yet been finally determined. The sensitivity is a parameter that indicates the sensitivity of the viscosity change of the easily condensable waxy crude oil to the operating parameters. The greater the sensitivity, the more sensitive the viscosity change of the easily condensable waxy crude oil is to the operating parameters. The smaller the sensitivity, the less sensitive the viscosity change of the easily condensable waxy crude oil is to the operating parameters.

[0095] In specific implementation, the prediction error can be determined based on all standardized data and all pending sensitivities in the following manner, namely: multiply the data at time j in each standardized data by the pending sensitivity of the corresponding standardized data, then sum the multiplied values, then subtract the viscosity value at time j in the viscosity data from the sum, square the obtained value, and use the obtained value as the error at time j, then sum the errors at all times, and divide the obtained value by twice the length of the viscosity data, and finally use the obtained value as the prediction error, where the minimum value of j is 1 and the maximum value is the length of the viscosity data.

[0096] It should be noted that the prediction error in this application refers to the error size when predicting the viscosity of the easily condensable waxy crude oil through the operating parameter data. The larger the prediction error, the larger the error when predicting the viscosity of the easily condensable waxy crude oil through the operating parameter data, and the smaller the prediction error, the smaller the error when predicting the viscosity of the easily condensable waxy crude oil through the operating parameter data.

[0097] In specific implementation, the first-order regularization constraint for determining all pending sensitivities may be implemented in the following manner, that is, the absolute values ​​of all pending sensitivities may be summed, and the obtained value may be used as the first-order regularization constraint for all pending sensitivities.

[0098] It should be noted that the regularization constraint is a parameter used to control the overfitting of the model. In this application, the first-order regularization constraint is used to screen suitable operating parameters to avoid overfitting parameters in the viscosity prediction of condensable waxy crude oil due to redundant data.

[0099] In specific implementation, determining the redundant deviation of all operating parameter data based on the prediction error and the first-order regularization constraint can be achieved in the following manner, namely: the sum obtained by adding the prediction error and the first-order regularization constraint can be used as the redundant deviation of all operating parameter data.

[0100] It should be noted that the redundant deviation in the present application is a parameter indicating the degree of deviation in the viscosity prediction of the easily condensable waxy crude oil caused by the redundant operating parameter data. The larger the redundant deviation, the larger the deviation in the viscosity prediction of the easily condensable waxy crude oil caused by the redundant operating parameter data. The smaller the redundant deviation, the smaller the deviation in the viscosity prediction of the easily condensable waxy crude oil caused by the redundant operating parameter data. Among them, the redundant operating parameter data refers to the operating parameter data that is irrelevant to the rheological state of the easily condensable waxy crude oil at the current moment.

[0101] In step 103, each operating parameter is optimized based on the redundant deviation, and then the sensitivity of the viscosity of the condensable waxy crude oil to the data change under different operating parameters is obtained, and a rheological-viscosity prediction model of the condensable waxy crude oil at the current moment is constructed according to all the sensitivities.

[0102] In specific implementation, each operating parameter is optimized based on the redundant deviation, and then the sensitivity of the viscosity of the easily condensable waxy crude oil to the data change under different operating parameters is obtained. This can be achieved in the following way, that is, each operating parameter can be optimized by the coordinate descent method in the prior art, and the vector composed of the undetermined sensitivity of each operating parameter is used as the weight vector, and then the redundant deviation is used as the output value of the loss function, the weight vector is continuously updated, and each weight in the weight vector finally output by the coordinate descent method is used as the sensitivity of the viscosity of the easily condensable waxy crude oil to the data change under different operating parameters.

[0103] It should be noted that the sensitivity in this application is a parameter indicating the sensitivity of the viscosity change of the easily condensable waxy crude oil to the operating parameters. The greater the sensitivity, the more sensitive the viscosity change of the easily condensable waxy crude oil is to the operating parameters. The smaller the sensitivity, the less sensitive the viscosity change of the easily condensable waxy crude oil is to the operating parameters.

[0104] In some embodiments, constructing a rheological-viscosity prediction model for the current moment of the easily condensable waxy crude oil based on all sensitivities can be achieved by the following steps:

[0105] Extract multiple effective parameters from all operating parameters according to all sensitivities;

[0106] The rheological-viscosity prediction model of the condensable waxy crude oil at the current moment is constructed based on all effective parameters.

[0107] In specific implementation, extracting multiple valid parameters from all operating parameters according to all sensitivities can be achieved in the following manner, namely: operating parameters whose absolute values ​​of sensitivities are less than a preset sensitivity threshold can be discarded as redundant parameters, and the remaining operating parameters can be used as valid parameters.

[0108] It should be noted that the sensitivity threshold in the present application can be preset to a very small positive number. For example, the sensitivity threshold can be preset to 0.05. In other embodiments, the sensitivity threshold can also be preset to other very small positive numbers, which is not limited here.

[0109] It should be noted that the effective parameters in this application refer to parameters that are closely related to the change in viscosity of the condensable waxy crude oil at the current moment.

[0110] In specific implementation, the rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment can be constructed according to all effective parameters in the following manner, that is, the rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment can be set as:

[0111]

[0112] Among them, P t is the viscosity of the waxy crude oil at time t, P t-1 is the viscosity of the waxy crude oil at time t-1, a e is the working parameter value of the e-th effective parameter at the current moment, b e is the sensitivity of the e-th valid parameter, M is the total number of valid parameters, and t is the current time.

[0113] It should be noted that the rheology-viscosity prediction model in the present application is a model for predicting the viscosity of crude oil based on the rheological properties of crude oil at the current moment. By inputting the observed values ​​of the operating parameters corresponding to the rheological properties of crude oil at the current moment into the model, the predicted value of crude oil viscosity can be obtained.

[0114] In step 104, various transportation parameters of the easily condensable waxy crude oil at the current moment are obtained, all the transportation parameters are input into the rheology-viscosity prediction model to obtain a predicted value of the viscosity of the easily condensable waxy crude oil, and the output power of the pour point depressant during the pipeline transportation of the easily condensable waxy crude oil is controlled according to the predicted value.

[0115] In specific implementation, the values ​​of various effective parameters of the condensable waxy crude oil at the detection point can be collected through the intelligent sensor, and the collected values ​​can be used as corresponding transportation parameters.

[0116] In addition, in the specific implementation, all the transport parameters are input into the rheology-viscosity prediction model to obtain the predicted value of the viscosity of the easily condensable waxy crude oil. This can be achieved in the following way, namely: each transport parameter is used as the operating parameter value of the effective parameter in the rheology-viscosity prediction model at the current moment, and then the value output by the rheology-viscosity prediction model is used as the predicted value of the viscosity of the easily condensable waxy crude oil.

[0117] In some embodiments, controlling the output power of the pour point depressant during pipeline transportation of the condensable waxy crude oil according to the predicted value can be achieved by the following steps:

[0118] When the predicted value exceeds a preset viscosity threshold, increasing the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil;

[0119] When the predicted value does not exceed the preset viscosity threshold, the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil is not adjusted.

[0120] It should be noted that the pour point reduction device in the present application may be a heating device for reducing the viscosity of easily condensed waxy crude oil. In other embodiments, it may also be other devices for reducing the viscosity of easily condensed waxy crude oil, such as an ultrasonic viscosity reduction device and an electromagnetic viscosity reduction device.

[0121] In specific implementation, when the predicted value exceeds the preset viscosity threshold, increasing the output power of the depressant during pipeline transportation of the easily condensable waxy crude oil can be achieved in the following manner, namely: the output power of the depressant during pipeline transportation of the easily condensable waxy crude oil can be increased by one kilowatt.

[0122] It should be noted that the viscosity threshold in the present application can be preset according to actual needs. For example, the viscosity threshold can be preset to 200 mPa·s. Those skilled in the art know that the change threshold can be preset to other values ​​according to actual needs, which falls within the protection scope of the present invention and will not be repeated here.

[0123] In addition, in another aspect of the present application, in some embodiments, the present application provides a pipeline transportation control system for easily condensable waxy crude oil, the pipeline transportation control system for easily condensable waxy crude oil includes a power control unit, reference Figure 4 , which is a schematic diagram of the structure of a power control unit according to some embodiments of the present application, the power control unit 400 includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0124] The collection module 401 in this application is mainly used to preset a detection point on the easily condensable waxy crude oil pipeline, and collect viscosity data and various operating parameter data of the easily condensable waxy crude oil at the detection point during the transportation process;

[0125] Processing module 402, in the present application, the processing module 402 is mainly used to determine the abnormal point of each operating parameter data according to the viscosity data, screen out multiple valid data of the easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determine the redundant deviation of all operating parameter data according to all the valid data;

[0126] It should be noted that the processing module 402 in the present application is also used to optimize various operating parameters based on the redundant deviation, thereby obtaining the sensitivity of the viscosity of the easily condensable waxy crude oil to the data changes under different operating parameters, and constructing a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment according to all the sensitivities;

[0127] Execution module 403, in the present application, execution module 403 is mainly used to obtain various transportation parameters of the easily condensable waxy crude oil at the current moment, input all the transportation parameters into the rheology-viscosity prediction model, obtain the predicted value of the viscosity of the easily condensable waxy crude oil, and control the output power of the decondensation device during the pipeline transportation of the easily condensable waxy crude oil according to the predicted value.

[0128] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned pipeline transportation control method for easily condensable waxy crude oil.

[0129] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a method for controlling the transportation of easily condensable waxy crude oil through a pipeline according to some embodiments of the present application. The method for controlling the transportation of easily condensable waxy crude oil through a pipeline in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0130] The processor 501 may be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0131] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0132] The memory 503 may 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, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0133] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The control method for pipeline transportation of easily condensable waxy crude oil in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0134] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0135] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0136] The above-mentioned computer device can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0137] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned pipeline transportation control method for easily condensable waxy crude oil is implemented.

[0138] In summary, in the control system and method for pipeline transportation of condensable waxy crude oil disclosed in the embodiment of the present application, first, by presetting detection points on the condensable waxy crude oil pipeline, and collecting viscosity data and various operating parameter data of the condensable waxy crude oil at the detection points during transportation; determining the abnormal points of each operating parameter data according to the viscosity data, screening out multiple valid data of the condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determining the redundant deviation of all operating parameter data according to all valid data; optimizing each operating parameter based on the redundant deviation, and then obtaining the sensitivity of the viscosity of the condensable waxy crude oil to the data change under different operating parameters, and constructing a rheological-viscosity prediction model of the condensable waxy crude oil at the current moment according to all sensitivities; obtaining various transportation parameters of the condensable waxy crude oil at the current moment, inputting all the transportation parameters into the rheological-viscosity prediction model, obtaining the predicted value of the viscosity of the condensable waxy crude oil, and controlling the output power of the decondensation device during the pipeline transportation of the condensable waxy crude oil according to the predicted value.

[0139] It can be seen that the present application extracts the abnormal points of the response of the change of viscosity of the easily condensable waxy crude oil to each operating parameter data, screens out the operating parameter data in the same rheological state (i.e., valid data), and evaluates how much redundant deviation will be generated when the viscosity of the easily condensable waxy crude oil is predicted directly through all valid data. Subsequently, the influence of each operating parameter on the viscosity of the easily condensable waxy crude oil is adaptively adjusted (i.e., each operating parameter is optimized based on the redundant deviation) to obtain the sensitivity of the change of viscosity of the easily condensable waxy crude oil to the response of each operating parameter. Subsequently, a rheological-viscosity prediction model is constructed based on all sensitivities, and the output power of the decondensation device during the pipeline transportation of the easily condensable waxy crude oil is controlled according to the prediction results of the rheological-viscosity prediction model to avoid the incorrect working power of the decondensation device due to prediction errors. In summary, the present application can select suitable operating parameters to predict the viscosity of crude oil, thereby reducing the additional consumption in the crude oil transportation operation.

[0140] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A pipeline transportation control method for easily condensable waxy crude oil, characterized in that: include: Preset detection points on the condensable waxy crude oil pipeline, and collect viscosity data and various operating parameter data of the condensable waxy crude oil at the detection points during transportation; Determine the abnormal point of each operating parameter data according to the viscosity data, screen out multiple valid data of the easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determine the redundant deviation of all operating parameter data according to all the valid data; Based on the redundant deviation, each operating condition parameter is optimized, and then the sensitivity of the viscosity of the easily condensable waxy crude oil to the data change under different operating condition parameters is obtained, and a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment is constructed according to all the sensitivities; The various transportation parameters of the easily condensable waxy crude oil at the current moment are obtained, all the transportation parameters are input into the rheology-viscosity prediction model to obtain the predicted value of the viscosity of the easily condensable waxy crude oil, and the output power of the pour point depressant during the pipeline transportation of the easily condensable waxy crude oil is controlled according to the predicted value.

2. The method according to claim 1, characterized in that Determining the abnormal point of each operating condition parameter data according to the viscosity data specifically includes: Selecting a working condition parameter data as selected working condition parameter data; Converting the selected operating condition parameter data into a selected operating condition sequence; Converting the viscosity data into a viscosity sequence; Determining the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods; Determine the abnormal point of the selected operating condition parameter data according to all the correlation degrees; Continue to determine the abnormal points of the remaining parameter data for each operating condition.

3. The method according to claim 2, characterized in that Determining the correlation between the selected operating condition sequence and the viscosity sequence in multiple time periods specifically includes: A comparison window is preset, and an operating condition subsequence and a viscosity subsequence within the same period are extracted from the selected operating condition sequence and the viscosity sequence through the comparison window; Determining the correlation between the operating condition subsequence and the viscosity subsequence; The operating condition subsequences and viscosity subsequences in other time periods are continuously intercepted from the selected operating condition sequence and the viscosity sequence through the comparison window until the number of interceptions reaches a preset cutoff threshold, thereby obtaining the correlations in multiple time periods.

4. The method according to claim 1, characterized in that Determine the redundant deviation of all operating parameter data based on all valid data, including: Standardize all valid data to obtain standardized data corresponding to each valid data; Determine the sensitivity of the change in viscosity of waxy crude oil to each operating parameter; Determine the prediction error based on all the standardized data and all the sensitivities to be determined; Determine first-order regularization constraints for all pending sensitivities; The redundant deviation of all operating condition parameter data is determined according to the prediction error and the first-order regularization constraint.

5. The method according to claim 1, characterized in that The current rheological-viscosity prediction model of the condensable waxy crude oil is constructed based on all sensitivities, including: Extract multiple effective parameters from all operating parameters according to all sensitivities; The rheological-viscosity prediction model of the condensable waxy crude oil at the current moment is constructed based on all effective parameters.

6. The method according to claim 1, characterized in that Controlling the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil according to the predicted value specifically includes: When the predicted value exceeds a preset viscosity threshold, increasing the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil; When the predicted value does not exceed the preset viscosity threshold, the output power of the pour point depressant during the pipeline transportation of the condensable waxy crude oil is not adjusted.

7. The method according to claim 1, characterized in that The decondensation device comprises: a heating device, an ultrasonic viscosity reduction device and an electromagnetic viscosity reduction device.

8. A pipeline transportation control system for easily condensable waxy crude oil, the pipeline transportation control system for easily condensable waxy crude oil comprising a power control unit, characterized in that: The power control unit comprises: A collection module is used to preset a detection point on the easily condensable waxy crude oil pipeline and collect viscosity data and various operating condition parameter data of the easily condensable waxy crude oil at the detection point during transportation; A processing module, used to determine the abnormal point of each operating parameter data according to the viscosity data, screen out multiple valid data of the easily condensable waxy crude oil in the same rheological state from the corresponding operating parameter data through each abnormal point, and determine the redundant deviation of all operating parameter data according to all the valid data; The processing module is also used to optimize various operating parameters based on the redundant deviation, thereby obtaining the sensitivity of the viscosity of the easily condensable waxy crude oil to the data changes under different operating parameters, and constructing a rheological-viscosity prediction model of the easily condensable waxy crude oil at the current moment according to all the sensitivities; The execution module is used to obtain various transportation parameters of the easily condensable waxy crude oil at the current moment, input all the transportation parameters into the rheology-viscosity prediction model, obtain the predicted value of the viscosity of the easily condensable waxy crude oil, and control the output power of the decondensation device during the pipeline transportation of the easily condensable waxy crude oil according to the predicted value.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the pipeline transportation control method for condensable waxy crude oil according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the pipeline transportation control method for easily condensable waxy crude oil according to any one of claims 1 to 7 is implemented.

Images