CN116151158A - Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline - Google Patents

Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline Download PDF

Info

Publication number
CN116151158A
CN116151158A CN202310443080.7A CN202310443080A CN116151158A CN 116151158 A CN116151158 A CN 116151158A CN 202310443080 A CN202310443080 A CN 202310443080A CN 116151158 A CN116151158 A CN 116151158A
Authority
CN
China
Prior art keywords
oil
conversion coefficient
measuring instrument
mixing interface
oil mixing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310443080.7A
Other languages
Chinese (zh)
Other versions
CN116151158B (en
Inventor
陈雷
袁子云
邵伟明
刘刚
姬浩洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China University of Petroleum East China
Original Assignee
China University of Petroleum East China
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China University of Petroleum East China filed Critical China University of Petroleum East China
Priority to CN202310443080.7A priority Critical patent/CN116151158B/en
Publication of CN116151158A publication Critical patent/CN116151158A/en
Application granted granted Critical
Publication of CN116151158B publication Critical patent/CN116151158B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Algebra (AREA)
  • Data Mining & Analysis (AREA)
  • Fluid Mechanics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Measuring Volume Flow (AREA)

Abstract

The invention belongs to the technical field of data processing, and provides a method and a system for tracking an oil mixing interface of a finished oil pipeline by fusing priori cognition, wherein a conversion coefficient of a measuring instrument is obtained based on information of the finished oil pipeline and historical operation data of the oil mixing interface; the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument; and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument. By incorporating the priori knowledge into the estimation process of the conversion coefficient of the measuring instrument, an accurate flow velocity prediction result of the oil mixing interface of the finished oil pipeline can be provided.

Description

Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a method and a system for tracking an oil mixing interface of a finished oil pipeline by fusing priori cognition.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The finished oil pipelines are used for continuously conveying various types of oil products according to a certain batch sequence, and oil mixing interfaces are generated between adjacent batches. The oil mixing interface position information is a core index for carrying out oil batch management on site, and the accurate tracking of the oil mixing interface depends on whether an on-site installed flowmeter can provide accurate flow information of oil transportation products. The flow speed of the oil mixing interface is affected by the operating parameters such as the pipe conveying pressure, the temperature and the like, and certain errors usually exist in positioning the information of the oil mixing interface directly based on the pipe conveying flow speed obtained by the measuring instrument, so that the on-site data are necessary to be combined to obtain the converted flow speed of the oil mixing interface, and an accurate data support is provided for accurately tracking the oil mixing interface. The prior patent CN115600516A proposes a method for establishing a pipeline flowmeter conversion method based on a machine learning algorithm and combining the pipe output and the oil mixing interface tracking historical data so as to improve the tracking precision of the oil mixing interface, but a pure data driving modeling method is easy to fall into a fitting error region, so that the converted tracking result is deviated from a true value of the position of the oil mixing interface, and the accurate tracking requirement of the oil mixing interface cannot be met.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the method and the system for tracking the oil mixing interface of the finished oil pipeline, which are integrated with the priori cognition, and can provide an accurate flow velocity prediction result of the oil mixing interface of the finished oil pipeline by incorporating the priori cognition into the estimation process of the conversion coefficient of the measuring instrument.
In order to achieve the above object, a first aspect of the present invention provides a method for tracking an oil mixing interface of a finished oil pipeline by fusing priori knowledge, comprising:
obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
The second aspect of the invention provides a finished oil pipeline oil mixing interface tracking system integrating priori knowledge, comprising:
an instrument conversion coefficient determination unit configured to: obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
a priori cognitive fusion unit configured to: the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
an oil mixing interface position output unit configured to: and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
The one or more of the above technical solutions have the following beneficial effects:
according to the invention, the conversion coefficient of the measuring instrument is obtained through the information of the finished oil pipeline and the historical operation data of the oil mixing interface, the prior distribution with physical significance is given to the conversion coefficient of the measuring instrument, the prior cognition is fused, the conversion coefficient of the measuring instrument is estimated by using the maximum posterior probability to obtain the estimated value of the conversion coefficient of the measuring instrument, and the position of the oil mixing interface is tracked according to the estimated value of the conversion coefficient of the measuring instrument. By incorporating the priori knowledge into the estimation process of the conversion coefficient of the measuring instrument, an accurate flow velocity prediction result of the oil mixing interface of the finished oil pipeline can be provided, and the method has important significance for improving the tracking accuracy of the oil mixing interface of the finished oil pipeline.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method for tracking a mixed oil interface of a finished oil pipeline by fusing priori knowledge in a first embodiment of the invention;
FIG. 2 shows a first embodiment of the present invention
Figure SMS_1
Different->
Figure SMS_2
Under the condition of that the conversion coefficient of the measuring instrument is +.>
Figure SMS_3
Is a priori distributed condition;
FIG. 3 shows a flow rate measurement of an oil-mixed interface without prior cognition
Figure SMS_4
True flow rate of interface with oil mixture>
Figure SMS_5
A comparison chart;
FIG. 4 is a flow rate of the oil-mixed interface based on least square method
Figure SMS_6
True flow rate of interface with oil mixture>
Figure SMS_7
A comparison chart;
FIG. 5 shows the flow rate of the oil-mixed interface based on the ridge regression method
Figure SMS_8
True flow rate of interface with oil mixture>
Figure SMS_9
A comparison chart;
FIG. 6 is a graph showing the oil mixing interface reduced flow rate obtained based on Gaussian mixture regression algorithm
Figure SMS_10
True flow rate of interface with oil mixture>
Figure SMS_11
A comparison chart;
FIG. 7 shows a reduced flow rate of a mixed oil interface obtained by a mixed oil interface tracking method based on a priori knowledge
Figure SMS_12
True flow rate of interface with oil mixture>
Figure SMS_13
Comparison graph.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
As shown in fig. 1, this embodiment discloses a method for tracking a mixed oil interface of a finished oil pipeline by fusing priori cognition, which includes:
step 1: obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
step 2: the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
step 3: and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
In step 1 of this embodiment, the information of the finished oil pipeline is obtained, including the pipe transportation distance between the stations at a certain station distance
Figure SMS_14
(unit: m); inner diameter of pipe->
Figure SMS_15
(unit: m). Further calculate the cross-sectional area of the tube>
Figure SMS_16
(Unit: m) 2 ）：
Figure SMS_17
（1）
The historical operation data of the oil mixing interface, including the operation flow of the oil transportation products, is obtained through the flow monitoring instrument between a certain station and the last station
Figure SMS_18
(Unit: m) 3 S), calculating the flow rate of the oil-mixed interface measurement>
Figure SMS_19
(unit: m/s):
Figure SMS_20
（2）
acquiring the first mixed oil concentration of the current station, namely 50% of mixed oil concentration, corresponding to the interface arrival time through monitoring equipment of a mixed oil interface of a certain station
Figure SMS_21
The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the first mixed oil concentration of the last station, namely 50% of mixed oil concentration, corresponding to interface outbound time +.>
Figure SMS_22
Calculating time difference +.>
Figure SMS_23
According to the above, calculating the true flow rate of the oil mixing interface +.>
Figure SMS_24
Units: m/s:
Figure SMS_25
（3）
measuring the flow velocity through the oil mixing interface obtained by the calculation
Figure SMS_26
True flow rate of interface with oil mixture>
Figure SMS_27
Can calculate the conversion coefficient of the measuring instrument +.>
Figure SMS_28
：
Figure SMS_29
（4）
In step 2 of this embodiment, in order to solve the problem of tracking the oil mixing interface of the oil production pipeline, the oil mixing interface is made to measure the flow velocity
Figure SMS_30
For inputting variable, the actual flow rate of the oil-mixed interface is +.>
Figure SMS_31
For output variables, the functional dependency of the two is as follows:
Figure SMS_32
（5）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_33
for outputting variable, i.e. actual flow rate of oil-mixing interface +.>
Figure SMS_34
，/>
Figure SMS_35
Measuring flow rate for input variables, i.e. oil mixing interfaces
Figure SMS_36
，/>
Figure SMS_37
The common Gaussian white noise in the measuring process is characterized by the average value of 0 and the variance of +.>
Figure SMS_38
Is a gaussian distribution of (c). Thus output variable +.>
Figure SMS_39
Following a gaussian distribution, the expression is as follows:
Figure SMS_40
（6）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_58
characterization of the given->
Figure SMS_43
And->
Figure SMS_57
Under the condition of->
Figure SMS_48
Probability density functions of (2); />
Figure SMS_54
Representing a gaussian distribution->
Figure SMS_46
And->
Figure SMS_52
The mean and variance in the gaussian distribution, exp represents an exponential function based on a natural constant e, respectively. Let->
Figure SMS_47
And->
Figure SMS_56
Respectively representing an input variable matrix and an output variable matrix, < + >>
Figure SMS_41
For training set sample size, +.>
Figure SMS_55
Characterization of->
Figure SMS_42
The training set samples are input with variable vectors, namely the flow rate of the oil mixing interface measurement>
Figure SMS_53
；/>
Figure SMS_45
Characterization of->
Figure SMS_51
The output variables of the training set samples, namely the actual flow rate of the oil mixing interface +.>
Figure SMS_44
T represents the transpose. In the conventional linear regression method, a least square method shown in the following formula (6) is generally used in combination with field data +.>
Figure SMS_49
Obtaining an estimation result of the conversion coefficient of the measuring instrument +.>
Figure SMS_50
：
Figure SMS_59
（7）
However, the data measurement process is difficult to avoid being interfered by noise, and the measurement equipment may have a certain deviation, so that a model overfitting phenomenon is easily caused, and a model prediction result is deviated.
The prior art adopts a ridge Regression method (Rigid Regression) shown in a formula (8), and a regularization term is added to improve the robustness of a data model, wherein
Figure SMS_60
Is regularized coefficient, but does not merge any prior cognition，/>
Figure SMS_61
Once the model is selected too much, the model is easy to fall into an under fitting error area, and the model effect is also not ideal.
Figure SMS_62
（8）
By analyzing the measuring instrument, the measured value may deviate from the actual value to some extent under the actual condition, but the deviation should not be too large, so that the ratio of the measured value to the actual value should fluctuate around 1. When the coefficient of conversion of the measuring instrument
Figure SMS_63
When the probability is far greater than or far less than 1, the serious fault of the flowmeter is caused, the samples are included in the training set and the conversion coefficient of the measuring instrument is estimated, so that a serious model overfitting phenomenon is caused, and the estimated value is seriously deviated from the real situation, so that the priori knowledge is needed to be integrated into the estimation process of the conversion coefficient of the measuring instrument.
In this embodiment, to incorporate the key priori knowledge, the measurement instrument is converted into coefficients
Figure SMS_64
The transformation is carried out, so that the prior distribution of the method follows Gaussian distribution; mean and variance are +.>
Figure SMS_65
And->
Figure SMS_66
. Based on priori knowledge, the conversion coefficient of the measuring instrument is endowed with a priori distribution with physical significance, so that +.>
Figure SMS_67
：
Figure SMS_68
（9）
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_71
representative Meter conversion coefficient->
Figure SMS_72
Probability density function of>
Figure SMS_77
Representing a gaussian distribution. From Bayesian law, the ∈box is known>
Figure SMS_70
Posterior probability +.>
Figure SMS_74
Proportional to +.>
Figure SMS_76
Is>
Figure SMS_78
And at->
Figure SMS_69
Under the condition->
Figure SMS_73
Likelihood function of +.>
Figure SMS_75
Can be expressed as:
Figure SMS_79
（10）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_80
characterizing the proportional relationship between the variables,
Figure SMS_81
. From equations (6) and (8), the likelihood function of the oil-mixing interface flow velocity data can be known>
Figure SMS_82
Is->
Figure SMS_83
Is>
Figure SMS_84
All follow a Gaussian distribution which satisfies the self-conjugated property, i.e. +.>
Figure SMS_85
The posterior probability of (2) also satisfies the gaussian distribution. The formulas (11), (12) respectively give logarithmic expressions of probability distributions of the two:
Figure SMS_86
（11）
Figure SMS_87
（12）
based on the formulas (11), (12) and Bayesian rule, it is possible to obtain
Figure SMS_88
The logarithmic form of posterior probability expression is:
Figure SMS_89
=/>
Figure SMS_90
（13）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_91
is->
Figure SMS_92
The superscript T indicates the transpose, < ->
Figure SMS_93
Is represented as a logarithmic function.
Based on post-maximizationThe idea of a posterior probability algorithm (Maximum a Posterior, MAP) is to relate the logarithmic posterior probability density function to
Figure SMS_94
The derivative can be obtained:
Figure SMS_95
（14）
let (14) be 0, the conversion coefficient of the measuring instrument can be obtained
Figure SMS_96
Is an estimated expression (15) of (2).
As can be seen from a comparison of the formulas (7) and (8), the addition of the amino acid sequence is given
Figure SMS_97
A Gaussian a priori distribution defined by equation (8) such that +.>
Figure SMS_98
The estimated value of (2) takes into account the data (>
Figure SMS_99
) On the carried information, the prior cognition is integrated>
Figure SMS_100
The acceptance degree of the priori knowledge is determined by
Figure SMS_101
And (5) determining.
Measurement noise is obtainable based on (16)
Figure SMS_102
Variance of->
Figure SMS_103
Is a function of the estimated expression of (2). Due to->
Figure SMS_104
And->
Figure SMS_105
The estimation processes of the two are mutually coupled, and the final estimation result of the two can be obtained by setting the iteration times to 10 times:
Figure SMS_106
（15）
Figure SMS_107
（16）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_109
and->
Figure SMS_113
Respectively representing an input variable matrix and an output variable matrix, < + >>
Figure SMS_115
For training set sample size, +.>
Figure SMS_110
Characterization of->
Figure SMS_112
Sample input variables of training set, i.e. measuring flow velocity of oil mixing interface
Figure SMS_114
；/>
Figure SMS_116
Characterization of->
Figure SMS_108
The output variables of the training set samples, namely the actual flow rate of the oil mixing interface +.>
Figure SMS_111
T represents the transpose.
In step 3 of this embodiment, the flow data of the oil transportation products is monitored by the flow measurement device between the current yard and the last yard
Figure SMS_117
In combination with the product oil pipeline size information->
Figure SMS_118
And->
Figure SMS_119
Calculating the flow rate of the mixed oil interface measurement>
Figure SMS_120
Estimated value of conversion coefficient combined with measuring instrument +.>
Figure SMS_121
Determining the actual flow rate of the oil mixing interface>
Figure SMS_122
Substitution time +.>
Figure SMS_123
And then calculating the position information of the oil mixing interface in the finished oil pipeline at any moment.
Specifically, based on flow measurement equipment between the current station and the last station, monitoring flow data of oil transportation products of a pipe to be tracked
Figure SMS_124
(Unit: m 3 S) in combination with the distance of the pipe transport between the stations of the finished product oil station +.>
Figure SMS_125
And the cross-sectional area of the tube>
Figure SMS_126
Calculating the corresponding oil mixing interface to be tracked to measure the flow rate +.>
Figure SMS_127
(unit: m/s):
Figure SMS_128
（17）
measuring instrument conversion coefficient estimation obtained through calculation in step 2Value of
Figure SMS_129
Determining the conversion flow rate of the oil mixing interface to be tracked>
Figure SMS_130
The expression is:
Figure SMS_131
（18）
the time of the departure and departure of the station yard is 0 time, and the time interval between the departure and departure of the station yard and the time of the station yard is 0 time is substituted into any time
Figure SMS_132
Obtaining the position information of the oil mixing interface to be tracked in the finished oil pipeline under the corresponding time node>
Figure SMS_133
(unit: m):
Figure SMS_134
（19）
wherein, the station yard is provided with a station outlet
Figure SMS_135
Is the origin of the coordinate system, +.>
Figure SMS_136
For the distance of the last station exit +.>
Figure SMS_137
Is a distance of (3). />
FIG. 2 shows respectively
Figure SMS_140
、/>
Figure SMS_142
Is->
Figure SMS_143
A priori distribution of time. Based on priori knowledge, realityUnder the condition that the measured value of the flow velocity of the oil mixing interface of the pipe transportation is possibly deviated from the actual value of the flow velocity of the oil mixing interface to a certain extent, but the deviation is not excessively large, so the ratio of the measured value to the actual value fluctuates around 1, thereby the conversion coefficient of the measuring instrument is ∈ ->
Figure SMS_138
Mean ∈in a priori distribution>
Figure SMS_141
Set to 1./>
Figure SMS_144
Control->
Figure SMS_145
Uncertainty of a priori distribution, ++>
Figure SMS_139
The larger the a priori distribution the more concentrated 1.
FIG. 3 shows the flow rate measured at the oil-mixing interface
Figure SMS_146
True flow rate of interface with oil mixture>
Figure SMS_147
In contrast, the oil mixing interface measures the flow velocity +.>
Figure SMS_148
True flow rate of interface with oil mixture>
Figure SMS_149
There is always a certain deviation.
FIG. 4 shows the oil mixing interface reduced flow rate obtained based on least squares
Figure SMS_150
True flow rate of interface with oil mixture>
Figure SMS_151
And (5) comparing. It can be seen that the light source is,the least square regression algorithm purely based on data driving has obvious overfitting phenomenon, and the phenomenon is shown that the predicted result still deviates from the actual value.
FIG. 5 shows the oil mixing interface reduced flow rate obtained based on the ridge regression method
Figure SMS_152
True flow rate of interface with oil mixture>
Figure SMS_153
In contrast, wherein->
Figure SMS_154
Taking 10. Because no priori cognition is fused, the model has a certain under fitting phenomenon, and the phenomenon is represented in the oil mixing interface to convert the flow rate +.>
Figure SMS_155
Always lower than the true flow rate of the oil interface>
Figure SMS_156
。
FIG. 6 shows the oil mixing interface reduced flow rate obtained based on Gaussian mixture regression algorithm
Figure SMS_157
True flow rate of interface with oil mixture>
Figure SMS_158
In contrast, the number of modes therein takes 3. Compared with the two methods, the Gaussian mixture regression algorithm considers the multi-modal characteristic of data hiding, so that the tracking accuracy of the oil-mixed interface is improved to a certain extent, and the model prediction effect is still poor.
FIG. 7 shows the oil-mixing interface conversion flow rate obtained by the oil-mixing interface tracking method fused with priori knowledge in the method of the invention
Figure SMS_159
True flow rate of interface with oil mixture>
Figure SMS_160
In contrast, wherein->
Figure SMS_161
Taking 10. For the inclusion of a priori knowledge into the measuring instrument conversion coefficient +.>
Figure SMS_162
Therefore, an accurate prediction result of the flow velocity of the oil mixing interface of the finished oil pipeline can be provided, and the modeling method has important significance for improving the tracking accuracy of the oil mixing interface of the finished oil pipeline.
Table 1 shows the determination of coefficients based on root mean square error RMSE
Figure SMS_163
And the maximum absolute error MAE index represents the flow velocity error, and the error index has the following calculation formula:
Figure SMS_164
（16）
Figure SMS_165
（17）
Figure SMS_166
（18）
wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure SMS_167
and->
Figure SMS_168
Characterization of the +.>
Figure SMS_169
True and fit values for individual samples, +.>
Figure SMS_170
Represents->
Figure SMS_171
Sample mean of>
Figure SMS_172
To test the sample size. />
Figure SMS_173
The closer to 1, the better the fitting effect is characterized. The smaller the root mean square error RMSE and the maximum absolute error MAE, the lower the overall error.
As can be obtained from table 1, the oil mixing interface tracking method of the finished oil pipeline integrating priori cognition provided by the invention has advantages in three error indexes, and the effectiveness of the modeling method is further verified.
TABLE 1 prediction error index of oil mixing interface flow velocity for different methods
Figure SMS_174
Table 2 shows the minimum, median and maximum values corresponding to the oil-mixed interface to station time deviation obtained based on the above method, in hours (h), and the method for calculating the to station time deviation is as follows, wherein
Figure SMS_175
Characterization of->
Figure SMS_176
The individual samples correspond to absolute values of the actual arrival time and the predicted arrival time differences of the oil mixing interface:
Figure SMS_177
（19）
the table 2 shows that the time deviation from the oil mixing interface to the station is larger in all other methods, but the prediction time deviation can be greatly reduced by adopting the method for tracking the oil mixing interface of the finished oil pipeline by fusing priori cognition, so that the method provided by the invention has important significance for improving the accuracy of tracking the oil mixing interface of the finished oil pipeline.
TABLE 2 predicting deviation of arrival time of oil mixing interfaces in different methods
Figure SMS_178
Example two
The purpose of this embodiment is to provide a blend oil interface tracking system of a finished oil pipeline that fuses priori cognition, including:
an instrument conversion coefficient determination unit configured to: obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
a priori cognitive fusion unit configured to: the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
an oil mixing interface position output unit configured to: and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
Specifically, the instrument conversion coefficient determination unit includes:
a first determination unit configured to: obtaining the cross-sectional area of the pipeline according to the inner diameter of the pipeline;
a second determination unit configured to: obtaining a mixed oil interface measurement flow rate by utilizing the running flow of the oil transportation product of the pipe and the cross section area of the pipe;
a third determination unit configured to: and determining a conversion coefficient of the measuring instrument based on the measured flow rate of the oil mixing interface and the actual flow rate of the oil mixing interface.
The a priori cognitive fusion unit further comprises:
a gaussian unit configured to: the prior probability density function of the conversion coefficient of the measuring instrument is enabled to accord with Gaussian distribution with the mean value of 1; according to the prior probability density function of the conversion coefficient of the measuring instrument, the Gaussian distribution with the mean value of 1 is met, and the likelihood function of the flow velocity data of the oil mixing interface is met, a logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument and a logarithmic expression of the likelihood function of the flow velocity data of the oil mixing interface are obtained;
a post-test unit configured to: obtaining a posterior probability expression of the logarithmic form of the conversion coefficient of the measuring instrument according to the logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument, the logarithmic expression of the likelihood function of the flow velocity data of the oil-mixing interface and the Bayes rule;
an estimation unit configured to: and deriving the logarithmic posterior probability expression about the conversion coefficient of the measuring instrument to obtain the estimated value of the conversion coefficient of the measuring instrument.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.

Claims (10)

1. A method for tracking a mixed oil interface of a finished oil pipeline by fusing priori cognition is characterized by comprising the following steps:
obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
2. The method for tracking the oil mixing interface of the finished oil pipeline by fusing priori knowledge according to claim 1, wherein the finished oil pipeline information comprises a pipeline section length and a pipeline inner diameter; the historical oil mixing interface operation data comprise the operation flow of the oil transportation product and the actual flow rate of the oil mixing interface.
3. The method for tracking the oil mixing interface of the finished oil pipeline by fusing priori knowledge according to claim 2, wherein the method is characterized in that the conversion coefficient of the measuring instrument is obtained based on the information of the finished oil pipeline and the operation data of the historical oil mixing interface, and is specifically as follows:
obtaining the cross-sectional area of the pipeline according to the inner diameter of the pipeline;
obtaining a mixed oil interface measurement flow rate by utilizing the running flow of the oil transportation product of the pipe and the cross section area of the pipe;
and determining a conversion coefficient of the measuring instrument based on the measured flow rate of the oil mixing interface and the actual flow rate of the oil mixing interface.
4. The method for tracking the oil mixing interface of the finished oil pipeline by fusing priori cognition according to claim 1, wherein the method for estimating the conversion coefficient of the measuring instrument by utilizing the maximum posterior probability by fusing priori cognition is specifically as follows:
the prior probability density function of the conversion coefficient of the measuring instrument is enabled to accord with Gaussian distribution with the mean value of 1;
according to the prior probability density function of the conversion coefficient of the measuring instrument, the Gaussian distribution with the mean value of 1 is met, and the likelihood function of the flow velocity data of the oil mixing interface is met, a logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument and a logarithmic expression of the likelihood function of the flow velocity data of the oil mixing interface are obtained;
obtaining a posterior probability expression of the logarithmic form of the conversion coefficient of the measuring instrument according to the logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument, the logarithmic expression of the likelihood function of the flow velocity data of the oil-mixing interface and the Bayes rule;
and deriving the logarithmic posterior probability expression about the conversion coefficient of the measuring instrument to obtain the estimated value of the conversion coefficient of the measuring instrument.
5. The method for tracking the oil mixing interface of the finished oil pipeline by fusing priori cognition according to claim 1, wherein the method for tracking the oil mixing interface of the finished oil pipeline is characterized by obtaining operation data of the oil mixing interface to be tracked and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument, and is specifically as follows:
obtaining the measured flow rate of the oil mixing interface to be tracked based on the flow data of the oil transportation product of the pipe to be tracked and the cross-sectional area of the oil transportation product of the finished product pipe;
obtaining the conversion flow rate of the oil mixing interface to be tracked by utilizing the conversion coefficient estimated value of the measuring instrument and the measurement flow rate of the oil mixing interface to be tracked;
and obtaining the position of the oil mixing interface to be tracked based on a certain time and the converted flow rate of the oil mixing interface to be tracked.
6. The method for tracking the oil mixing interface of the finished oil pipeline with the fusion of priori knowledge according to claim 2, wherein the determination of the actual flow rate of the oil mixing interface is as follows:
determining the time difference of the first mixed oil concentration and the second mixed oil concentration according to the arrival time of the mixed oil interface corresponding to the first mixed oil concentration of the current station and the arrival time of the mixed oil interface corresponding to the first mixed oil concentration of the last station;
and determining the actual flow rate of the oil mixing interface based on the pipe conveying distance between the current station and the last station and the time difference of the current station and the last station.
7. The method for tracking the oil mixing interface of the finished oil pipeline by fusing priori knowledge according to claim 5, wherein the time of the departure and the arrival of the station is 0 time, and the interval between the time and the 0 time istMultiplying the arbitrary time of the interface conversion flow rate of the oil mixing to be tracked to obtain the arbitrary timetThe corresponding oil mixing interface is at a position away from the station exit of the last station.
8. A product oil pipeline oil mixing interface tracking system integrating priori cognition is characterized by comprising:
an instrument conversion coefficient determination unit configured to: obtaining a conversion coefficient of the measuring instrument based on the finished oil pipeline information and the historical oil mixing interface operation data;
a priori cognitive fusion unit configured to: the prior cognition is fused, and the maximum posterior probability is utilized to estimate the conversion coefficient of the measuring instrument to obtain an estimated value of the conversion coefficient of the measuring instrument;
an oil mixing interface position output unit configured to: and acquiring operation data of the oil mixing interface to be tracked, and determining the position of the oil mixing interface to be tracked by combining the estimated value of the conversion coefficient of the measuring instrument.
9. The prior-awareness-fused oil-mixing interface tracking system of a finished oil pipeline according to claim 8, wherein the instrument conversion coefficient determining unit comprises:
a first determination unit configured to: obtaining the cross-sectional area of the pipeline according to the inner diameter of the pipeline;
a second determination unit configured to: obtaining the flow rate of the oil mixing interface measurement by utilizing the running flow of the oil transportation product of the pipe and the cross-sectional area of the pipe;
a third determination unit configured to: and determining a conversion coefficient of the measuring instrument based on the measured flow rate of the oil mixing interface and the actual flow rate of the oil mixing interface.
10. The system for tracking the oil mixing interface of the finished oil pipeline fused with priori knowledge according to claim 8, wherein the priori knowledge fusion unit comprises:
a gaussian unit configured to: the prior probability density function of the conversion coefficient of the measuring instrument is enabled to accord with Gaussian distribution with the mean value of 1; according to the prior probability density function of the conversion coefficient of the measuring instrument, the Gaussian distribution with the mean value of 1 is met, and the likelihood function of the flow velocity data of the oil mixing interface is met, a logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument and a logarithmic expression of the likelihood function of the flow velocity data of the oil mixing interface are obtained;
a post-test unit configured to: obtaining a posterior probability expression of the logarithmic form of the conversion coefficient of the measuring instrument according to the logarithmic expression of the probability density function of the conversion coefficient of the measuring instrument, the logarithmic expression of the likelihood function of the flow velocity data of the oil-mixing interface and the Bayes rule;
an estimation unit configured to: and deriving the logarithmic posterior probability expression about the conversion coefficient of the measuring instrument to obtain the estimated value of the conversion coefficient of the measuring instrument.
CN202310443080.7A 2023-04-24 2023-04-24 Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline Active CN116151158B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310443080.7A CN116151158B (en) 2023-04-24 2023-04-24 Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310443080.7A CN116151158B (en) 2023-04-24 2023-04-24 Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline

Publications (2)

Publication Number Publication Date
CN116151158A true CN116151158A (en) 2023-05-23
CN116151158B CN116151158B (en) 2023-07-18

Family

ID=86354764

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310443080.7A Active CN116151158B (en) 2023-04-24 2023-04-24 Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline

Country Status (1)

Country Link
CN (1) CN116151158B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116307303A (en) * 2023-05-24 2023-06-23 中国石油大学(华东) Mechanism-data dual-drive oil mixing length prediction method and system for finished oil pipeline

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6182013B1 (en) * 1999-07-23 2001-01-30 Schlumberger Technology Corporation Methods and apparatus for dynamically estimating the location of an oil-water interface in a petroleum reservoir
CN102606887A (en) * 2011-01-25 2012-07-25 中国石油天然气集团公司 Judgment method for oil mixture interface positions in sequential pipelining by product oil pipeline
CN104655396A (en) * 2015-02-15 2015-05-27 中国石油大学(华东) Multiphase flow simulation test device and method for refined oil product with water and impurities
US20200372195A1 (en) * 2019-05-24 2020-11-26 Ledaflow Technologies Da Method and tool for planning and dimensioning subsea pipelines for produced fluids
CN115600516A (en) * 2022-09-30 2023-01-13 国家石油天然气管网集团有限公司（Cn） Method and device for tracking position of oil mixing interface, electronic equipment and medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6182013B1 (en) * 1999-07-23 2001-01-30 Schlumberger Technology Corporation Methods and apparatus for dynamically estimating the location of an oil-water interface in a petroleum reservoir
CN102606887A (en) * 2011-01-25 2012-07-25 中国石油天然气集团公司 Judgment method for oil mixture interface positions in sequential pipelining by product oil pipeline
CN104655396A (en) * 2015-02-15 2015-05-27 中国石油大学(华东) Multiphase flow simulation test device and method for refined oil product with water and impurities
US20200372195A1 (en) * 2019-05-24 2020-11-26 Ledaflow Technologies Da Method and tool for planning and dimensioning subsea pipelines for produced fluids
CN115600516A (en) * 2022-09-30 2023-01-13 国家石油天然气管网集团有限公司（Cn） Method and device for tracking position of oil mixing interface, electronic equipment and medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
RACHID F. B. FREITAS等: "Predicting Mixing Volumes in Serial Transport in Pipelines", 《JOURNAL OF FLUIDS ENGINEERING》 *
沈瑞灏: "成品油管道批次位置跟踪及溯源研究", 《知网》 *
袁子云等: "融合机制与高斯混合回归算法的成品油管道顺序输送混油长度预测模型", 《中国石油大学学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116307303A (en) * 2023-05-24 2023-06-23 中国石油大学(华东) Mechanism-data dual-drive oil mixing length prediction method and system for finished oil pipeline
CN116307303B (en) * 2023-05-24 2023-09-26 中国石油大学(华东) Mechanism-data dual-drive oil mixing length prediction method and system for finished oil pipeline

Also Published As

Publication number Publication date
CN116151158B (en) 2023-07-18

Similar Documents

Publication Publication Date Title
CN107765347B (en) Short-term wind speed prediction method based on Gaussian process regression and particle filtering
CN116151158B (en) Priori cognition fusion based oil mixing interface tracking method and system for finished oil pipeline
JP2021051769A (en) Data cleansing system and method for inferring feed composition
CN105841762B (en) The flow metering method and system of ultrasonic water meter
US10788356B2 (en) Method of inspecting gas supply system, method of calibrating flow controller, and method of calibrating secondary reference device
JP2016224947A (en) Measurement sample extraction method with sampling rate decision mechanism, and computer program product therefor
TW200949596A (en) Server and system and method for automatic virtual metrology
CN109917152B (en) Method for measuring average flow velocity of vertical line
JP5164954B2 (en) Device diagnostic method and device diagnostic device
CN109446669B (en) Soft measurement method for ore pulp concentration
CN110632625B (en) GNSS time series step detection and repair method
CN115600516A (en) Method and device for tracking position of oil mixing interface, electronic equipment and medium
CN112539809A (en) Intelligent water meter operation error calibration method and device based on Internet of things service and storage medium
Lin et al. A novel efficient model for gas compressibility factor based on GMDH network
Subali et al. A new model for measuring the complexity of SQL commands
US9255827B2 (en) Computer based fluid flow velocity estimation from concentrations of a reacting constituent for products and services
JP2022151193A (en) Device, method and program
CN113959511B (en) Flow metering method, equipment, medium and product based on jet flow water meter
CN110672058B (en) On-line calibration data sequence matching method and device of sensor for structure monitoring
CN112580183B (en) Real-time flow accurate control method for online learning water pump model
US11047722B2 (en) Computer based fluid flow velocity estimation from concentrations of a reacting constituent for products and services
CN107655549A (en) A kind of intelligent gas meter is in Line synthesis error calibration method
Pang et al. RUL prediction for bivariate degradation process considering individual differences
CN114580214B (en) Intelligent steam flowmeter checking and testing system and method based on Internet of things
RU135795U1 (en) INSTALLATION FOR VERIFICATION AND CALIBRATION OF METERS, FLOW METERS AND FLOW METERS-GAS METERS

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant