CN108254038A - A kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods - Google Patents

A kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods Download PDF

Info

Publication number
CN108254038A
CN108254038A CN201711448735.0A CN201711448735A CN108254038A CN 108254038 A CN108254038 A CN 108254038A CN 201711448735 A CN201711448735 A CN 201711448735A CN 108254038 A CN108254038 A CN 108254038A
Authority
CN
China
Prior art keywords
data
oil
water interfaces
threshold value
water
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
CN201711448735.0A
Other languages
Chinese (zh)
Other versions
CN108254038B (en
Inventor
任喜伟
何立风
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.)
Shaanxi University of Science and Technology
Original Assignee
Shaanxi University of Science and Technology
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 Shaanxi University of Science and Technology filed Critical Shaanxi University of Science and Technology
Priority to CN201711448735.0A priority Critical patent/CN108254038B/en
Publication of CN108254038A publication Critical patent/CN108254038A/en
Application granted granted Critical
Publication of CN108254038B publication Critical patent/CN108254038B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01FMEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
    • G01F23/00Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fluid Mechanics (AREA)
  • Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

A kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging to calculate method, intermediate value pre-processes cluster calculation method, the computational methods are based on K means clustering algorithm basic thoughts, eliminate pseudo- data using intermediate value Preprocessing Algorithm first, obtain the optimization data for being conducive to classification;Secondly data mining technology is utilized, using multiple threshold value clustering algorithm, constantly correct initial threshold, so as to obtain one group of optimal threshold, and finally oil/water interface level height is acquired according to the method for statistic of classification, realize that oil-water interfaces accurately measure, computational methods proposed by the present invention are more more stable than Traditional calculating methods, more accurate, more intelligent, are well-suited for crude oil storage tank oil-water interfaces monitoring system and provide accurate monitoring data.

Description

A kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods
Technical field
The present invention relates to crude oil storage tank oil-water interfaces field of measuring technique more particularly to a kind of crude oil storage tank oil-water interfaces numbers According to the computational methods for going pseudo- and level gauging.
Background technology
Mined crude oil is transported to multi-purpose station, is stored in crude oil storage tank, first passes through sedimentation, then carries out grease point From later, the oil for refinement finally can be just obtained.During water-oil separating, need to oil reservoir, water in crude oil storage tank The height of layer and emulsion layer is identified and measures, and oil-water interfaces measuring technique arises.In order to detect in infall process Settling tank oil-water interfaces and liquid level need that oil reservoir, water layer and emulsification layer height in crude oil storage tank are identified and surveyed Amount.The method of identification and detection mainly has float-type, condenser type, ultrasonic type, magnetostriction type, guided wave radar formula, radio frequency to lead Receive formula, air blowing type and optical fiber type etc..Although these method correlation scholar, experts have done a large amount of research and experiment, and obtain Good theory and practice effect, but with regard to current sector application from the perspective of, by site environment, fund input, technology The factors such as condition limit, and only Part Methods have been obtained commonly used and promoted.
In contrast, radio frequency admittance formula and guided wave radar formula detection method are easy to develop and promote, and are most widely used.Profit With different medium in radio frequency admittance material level control technology or electromagnetic wave echo detecting technology perception settling tank, obtain different size of Analog signal by signal conversion processing, obtains being easy to the liquid level data of analysis, and after being counted, calculating to liquid level data, It can obtain the information such as oil-water interfaces and liquid level, volume in settling tank.But to oil-water interfaces digital signal statistics, It, on the one hand can be because of some the pseudo- data obtained in measurement so that measurement result is larger with actual deviation, another during calculating It is improper that aspect can be chosen because of the representative value in oil-water interfaces data, and survey calculation method falls behind, and leads to measurement result and reality not Symbol.In recent years, related scholar, expert for oil-water interfaces it is pseudo- it is data-optimized carried out to oil-water interfaces survey calculation method it is related Research.Such as, it is proposed that optimize the algorithm of pseudo- data in optimization oil-water interfaces data, there is most value filter algorithm, fixed point to correct and calculate Method and region Denoising Algorithm.It is calculated, and propose in addition, classical K-means clustering algorithms are introduced oil/water interface level height Improved K-means clustering algorithms.These algorithms can optimize oil-water interfaces data under certain conditions simultaneously can accurately calculate oil Water termination and liquid level, but fail to optimize the method for data and divide the method most preferably clustered effectively to unite, into And optimize oil-water interfaces data, fast and accurately obtain oil-water interfaces and liquid level.
Invention content
For overcome the deficiencies in the prior art, the present invention provides a kind of crude oil storage tank oil-water interfaces data and pseudo- and liquid level is gone to survey The computational methods of amount, intermediate value pre-process cluster calculation method, increase the stability, correctness and intelligent, improvement grease of algorithm Interface calculating process ensures that oil-water interfaces result of calculation is more accurate.
To achieve these goals, the invention is realized by the following technical scheme:
A kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods, include the following steps;
The first step obtains interface data Di(i=1,2,3 ..., N);
Second step establishes median filter template, and template width S, template is interior comprising S data, and data in template are arranged Sequence asks for median Dm;Entire oil-water interfaces data are traversed, and successively by D with templatemIt is assigned to first position pair in template The D answeredi, i.e., D is given againiAssignment obtains one group of interface data D optimizedi' (i=1,2,3 ..., N);
Third walks, to new interface data Di' carry out ascending sequence (quick sorting algorithm);
4th step chooses four oil-water interfaces data M1, M2, M3, M4Respectively as gas-bearing formation, oil reservoir, emulsion layer and water layer Representative value, and set three initial threshold Y1、Y2、Y3Respectively as the threshold value of gas-bearing formation, oil reservoir, emulsion layer and water layer, threshold value is calculated Method it is as follows:
Y1=(M1+M2)/2
Y2=(M2+M3)/2
Y3=(M3+M4)/2
(1)
5th step divides data acquisition system classification according to threshold value, and setting A, B, C, D represent four data collection class, meet data Set A's belongs to gas-bearing formation data, and meet data acquisition system B belongs to oil reservoir, and meet data acquisition system C belongs to emulsion layer, meets number According to the water layer that belongs to of set D, statistical data collection approach is as follows:
A={ x ∈ Di|x≤Y1}
B={ x ∈ Di|Y1< x≤Y2}
C={ x ∈ Di|Y2< x≤Y3}
D={ x ∈ Di|Y3< x }
(2)
6th step, statistics meets each layer data number of data acquisition system range, respectively with N1、N2、N3、N4Represent set A, B, C, D In data amount check, ∑ { A }, ∑ { B }, ∑ { C }, ∑ { D } represent the sum of data included in set A, B, C, D respectively, calculates New threshold value Y1、Y2、Y3Computational methods are as follows:
Y1=(∑ { A }/N1+∑{B}/N2)/2
Y2=(∑ { B }/N2+∑{C}/N3)/2
Y3=(∑ { C }/N3+∑{D}/N4)/2
(3)
7th step repartitions set A, B, C, D, and recalculate newest threshold value Y according to the 6th step according to the 5th step1、Y2、Y3, This process is constantly repeated, recurrence does not change, optimal threshold goes out until newest threshold value restrains before and after that is, newest threshold value Until existing;
8th step, data acquisition system A, B, C, D that statistics finally determines, obtains N1、N2、N3、N4, and respectively with H1、H2、H3、H4 It represents the medium level of gas-bearing formation, oil reservoir, emulsion layer, water layer, spacing between each sensor of measuring device is represented with h, survey is represented with L Height of the bottom of device apart from tank bottom is measured, the method for calculating each layer medium level is as follows:
H1=N1×h
H2=N2×h
H3=N3×h
H4=N4×h+L
(4)。
Beneficial effects of the present invention:
Intermediate value pretreatment cluster calculation method result of calculation proposed by the present invention and liquid level actual height one in crude oil storage tank It causes, computational methods result correctness is verified.Therefore, intermediate value pretreatment cluster calculation method can effectively shield grease circle Pseudo- data in face data, and different repeatedly threshold calculations choose optimal threshold, finally calculate accurate oil-water interfaces and liquid level Highly.Relative to traditional classification statistical calculation method, on the one hand intermediate value pretreatment cluster calculation method can effectively shield pseudo- number According on the other hand by data mining, being not entirely dependent on initial threshold, but final threshold adaptively obtained by initial threshold Value, final threshold value is constantly to be excavated by algorithm, correct one group of reasonable threshold value that initial threshold obtains.Therefore, intermediate value pre-processes Cluster calculation method is more stable compared with Traditional calculating methods, and accuracy is higher, and algorithm is more intelligent, is a kind of feasible crude oil storage tank oil Water termination DATA REASONING computational methods.
Description of the drawings
Fig. 1 is the crude oil storage tank oil-water interfaces instrumentation plan of the present invention.
Fig. 2 is the oil-water interfaces data graphs of the present invention.
Fig. 3 is the oil-water interfaces data graphs for including pseudo- data of the present invention.
The intermediate value that Fig. 4 is the present invention pre-processes poly- computational methods program flow diagram.
The median filter that Fig. 5 is the present invention models schematic diagram.
Fig. 6 is median filter of the present invention treated oil-water interfaces data graphs.
Specific embodiment
The present invention is described in detail with reference to the accompanying drawings and in conjunction with the embodiments.
The variation of medium can cause the variation of many physical quantitys in certain space, such as:Electric field, magnetic field etc.;These objects The variation of reason amount will indirectly reflect and represent the variation of medium unit volume and dielectric property, be in line generally with surveyed medium Sexual intercourse.Therefore, the sensing rapier structure of associate(d) matrix formula distribution, in the orderly control of high speed lsi microcontroller Under, the change information of these physical quantitys is obtained in real time, and these information are analyzed, are calculated, according to certain rules the amount of progress Change processing, conversion just can accurately know the variation i.e. change of medium liquid level, level of medium unit volume and dielectric property Change, and the variable quantity of medium liquid level, level is converted into industrial standard electric signal output and passes to DCU, DCS, PLC, industry The collecting devices such as acquisition module, industrial control computer monitor oil-water interfaces in real time for administrative department.
To be tested 12 meters of crude oil storage tank height, 12 meters of diameter distributed 101 sensors on oil-water surface measuring instrument, pass 0.1 meter of sensor spacing, measuring instrument is for 2 meters of tank bottom, referring to Fig. 1.There are gas-bearing formation, oil reservoir, emulsion layer and water in crude oil storage tank Layer.Oil-water interface measurement mechanism uses the sensing rapier structure of matrix form distribution, and N number of level is formed between medium or tank skin Detect cross section, measuring device under the control of cpu, receiving sensor perceive analog signal amount, by filtering, demodulating, mould Number conversion becomes digital signal, is ultimately passed to host computer, and oil-water interfaces data are obtained by calculating.The data that host computer receives As shown in table 1, curve graph is as shown in Figure 2.It is known that being macroscopically in the medium of different level from data, data Characterization is substantially close, is conducive to distinguish different medium in crude oil storage tank.
Table 1
Oil-water interfaces data instance of the table 1 for the present invention.
Calculating process is divided into three steps:The first step needs manually to choose four typical cases in each layer media data of oil-water interfaces Value, and pass through representative value and calculate each layer classification thresholds;Second step meets each layer data of range according to each layer classification thresholds statistics Number;Third walks, and the relevant informations such as each layer medium level, volume is calculated, so as to obtain oil-water interface position.
However, on the one hand because traditional classification statistical calculation method is needed before artificial selected threshold or initial barycenter are suitable It puts, could accurately find oil-water interfaces and calculates liquid level, conversely, measurement result has very big error;On the other hand by The influence to float up and down to measurement data, there are previous data to represent the first medium, and the latter data represent second of Jie Matter, and third data represent the possibility of the first medium, do not meet the regularity of distribution of medium in crude oil storage tank completely, this Kind situation is considered the presence of pseudo- data in oil-water interfaces data.So-called puppet data are exactly because of measuring device and original in measurement process Certain existing subjective factor causes in itself for certain existing objective factor or measuring device sensor between oil tank shape A kind of wrong data.As shown in figure 3, it is 45 that wherein 21 numbers, which are 862,93 numbers, hence it is evident that for pseudo- data.If still Oil-water interfaces height is calculated according to Traditional calculating methods, then result of calculation does not conform to the actual conditions, it is therefore desirable to propose new method solution The certainly above problem.
The implementation process of the present invention is described in further detail below:
The present invention is suitable for calculating crude oil storage tank oil-water interfaces and liquid level, particularly settling tank, knockout drum, sewage The oil-water interfaces and liquid level of the oil tanks such as tank, holding vessel, oil-water interfaces real time monitoring and inventory making system for multi-purpose station provide Accurate Data safeguard.The present invention proposes that a kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods --- Intermediate value pre-processes cluster calculation method.Increase the stability, correctness and intelligent, improvement oil-water interfaces calculating process of algorithm, Ensure that oil-water interfaces result of calculation is more accurate.Circular of the present invention is described as follows:
Intermediate value pretreatment cluster calculation method be herein analysis oil-water interfaces Traditional calculating methods it is insufficient on the basis of, carry A kind of new oil-water interfaces computational methods gone out.The computational methods basic thought is as follows:
1. oil-water interfaces data D is eliminated using intermediate value Preprocessing Algorithm firstiPseudo- number present in (i=1,2,3 ..., N) According to eliminating wrong data smaller or larger in same medium, the oil-water interfaces data after optimization made more to accurately reflect reality Medium speciality.
2. pretreatment, ascending sequence, the oil-water interfaces after sequence are ranked up to the oil-water interfaces data after optimization Data are convenient for preferably finding cluster centre, more suitable for partition clustering.
3. after oil-water interfaces data prediction, proposing the thought based on classical K-means cluster calculations method, constantly classify Oil-water interfaces initial threshold in update traditional classification computational methods, obtains oil-water interface position.
Intermediate value pretreatment cluster calculation method main program flow chart is as shown in Figure 4.It is as follows:
The first step obtains interface data Di(i=1,2,3 ..., N), oil-water interfaces data are as shown in table 1.
Second step establishes median filter template, template width S, as shown in figure 5, comprising S data in template, to mould Data sorting in plate asks for median Dm;Entire oil-water interfaces data are traversed, and successively by D with templatemIs assigned in template The corresponding D in one positioni, i.e., D is given againiAssignment obtains one group of interface data D optimizedi' (i=1,2,3 ..., N), such as Shown in Fig. 6.Wherein, No. 21 pseudo- data are optimized for 62, No. 93 pseudo- data by original 862 and are optimized for 3996 by original 45.In Value filtering optimization process main program pseudocode is as follows:
%GetMed functions
GetMed(x)
|for j←1to j<S do
||if x[j]>x[j+1]
|||p←x[j]
|||x[j]←x[j+1]
|||x[j+1]←p
||end of if
||j←j+1
|end of for
|Dm←x[(S+1)/2]
end of GetMed
Third walks, to new interface data Di' carry out ascending sequence (quick sorting algorithm).
4th step chooses four oil-water interfaces data M1, M2, M3, M4Respectively as gas-bearing formation, oil reservoir, emulsion layer and water layer Representative value, M1Take 15 numbers 50, M2Take 64 numbers 564, M3Take 76 numbers 1228, M490 numbers 3996 are taken, and are set Three initial threshold Y1、Y2、Y3Respectively as the threshold value of gas-bearing formation, oil reservoir, emulsion layer and water layer, the method for calculating threshold value is as follows.Meter Initial threshold Y after calculation1=307, Y2=896, Y3=2612.
Y1=(M1+M2)/2
Y2=(M2+M3)/2
Y3=(M3+M4)/2
(1)
5th step divides data acquisition system classification according to threshold value, and setting A, B, C, D represent four data collection class, meet data Set A's belongs to gas-bearing formation data, and meet data acquisition system B belongs to oil reservoir, and meet data acquisition system C belongs to emulsion layer, meets number According to the water layer that belongs to of set D, statistical data collection approach is as follows:
A={ x ∈ Di|x≤Y1}
B={ x ∈ Di|Y1< x≤Y2}
C={ x ∈ Di|Y2< x≤Y3}
D={ x ∈ Di|Y3< x }
(2)
6th step, statistics meets each layer data number of data acquisition system range, respectively with N1、N2、N3、N4Represent set A, B, C, D In data amount check, ∑ { A }, ∑ { B }, ∑ { C }, ∑ { D } represent the sum of data included in set A, B, C, D respectively, calculates New threshold value Y1、Y2、Y3Computational methods are as follows:
Y1=(∑ { A }/N1+∑{B}/N2)/2
Y2=(Σ { B }/N2+Σ{C}/N3)/2
Y3=(∑ { C }/N3+∑{D}/N4)/2
(3)
7th step repartitions set A, B, C, D, and recalculate newest threshold value Y according to the 6th step according to the 5th step1、Y2、Y3, This process is constantly repeated, recurrence does not change, optimal threshold goes out until newest threshold value restrains before and after that is, newest threshold value Until existing.It is respectively Y by calculating optimal threshold1=339, Y2=925, Y3=2525.
8th step, data acquisition system A, B, C, D that statistics finally determines, obtains N1、N2、N3、N4, and respectively with H1、H2、H3、H4 It represents the medium level of gas-bearing formation, oil reservoir, emulsion layer, water layer, spacing between each sensor of measuring device is represented with h, survey is represented with L Height of the bottom of device apart from tank bottom is measured, the method for calculating each layer medium level is as follows.Data acquisition system is obtained by statistics Number is respectively N1=57, N2=15, N3=6, N4=43, H is calculated1=5.7 meters, H2=1.5 meters, H3=0.6 meter, H4= 4.3 meters, result of calculation and actual liquid level in crude oil storage tank are highly consistent.

Claims (1)

1. a kind of crude oil storage tank oil-water interfaces data go pseudo- and level gauging computational methods, which is characterized in that including following step Suddenly;
The first step obtains interface data Di(i=1,2,3 ..., N);
Second step establishes median filter template, and template width S, template is interior comprising S data, to data sorting in template, asks Take median Dm;Entire oil-water interfaces data are traversed, and successively by D with templatemIt is corresponding to be assigned to first position in template Di, i.e., D is given againiAssignment obtains one group of interface data D optimizedi' (i=1,2,3 ..., N);
Third walks, to new interface data Di' carry out ascending sequence;
4th step chooses four oil-water interfaces data M1, M2, M3, M4Respectively as the typical case of gas-bearing formation, oil reservoir, emulsion layer and water layer Value, and set three initial threshold Y1、Y2、Y3Respectively as the threshold value of gas-bearing formation, oil reservoir, emulsion layer and water layer, the side of threshold value is calculated Method is as follows:
Y1=(M1+M2)/2
Y2=(M2+M3)/2
Y3=(M3+M4)/2
(1)
5th step divides data acquisition system classification according to threshold value, and setting A, B, C, D represent four data collection class, meet data Set A's belongs to gas-bearing formation data, and meet data acquisition system B belongs to oil reservoir, and meet data acquisition system C belongs to emulsion layer, meets number According to the water layer that belongs to of set D, statistical data collection approach is as follows:
A={ x ∈ Di|x≤Y1}
B={ x ∈ Di|Y1< x≤Y2}
C={ x ∈ Di|Y2< x≤Y3}
D={ x ∈ Di|Y3< x }
(2)
6th step, statistics meets each layer data number of data acquisition system range, respectively with N1、N2、N3、N4Represent set A, B, C, D In data amount check, ∑ { A }, ∑ { B }, ∑ { C }, ∑ { D } represent the sum of data included in set A, B, C, D respectively, calculates New threshold value Y1、Y2、Y3Computational methods are as follows:
Y1=(∑ { A }/N1+∑{B}/N2)/2
Y2=(∑ { B }/N2+∑{C}/N3)/2
Y3=(∑ { C }/N3+∑{D}/N4)/2
(3)
7th step repartitions set A, B, C, D, and recalculate newest threshold value Y according to the 6th step according to the 5th step1、Y2、Y3, This process is constantly repeated, recurrence does not change, optimal threshold goes out until newest threshold value restrains before and after that is, newest threshold value Until existing;
8th step, data acquisition system A, B, C, D that statistics finally determines, obtains N1、N2、N3、N4, and respectively with H1、H2、H3、H4It represents Gas-bearing formation, oil reservoir, emulsion layer, water layer medium level, spacing between each sensor of measuring device is represented with h, represents to measure dress with L The height of distance from bottom tank bottom is put, the method for calculating each layer medium level is as follows:
CN201711448735.0A 2017-12-27 2017-12-27 A kind of crude oil storage tank oil-water interfaces data go the calculation method of puppet and level gauging Active CN108254038B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711448735.0A CN108254038B (en) 2017-12-27 2017-12-27 A kind of crude oil storage tank oil-water interfaces data go the calculation method of puppet and level gauging

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711448735.0A CN108254038B (en) 2017-12-27 2017-12-27 A kind of crude oil storage tank oil-water interfaces data go the calculation method of puppet and level gauging

Publications (2)

Publication Number Publication Date
CN108254038A true CN108254038A (en) 2018-07-06
CN108254038B CN108254038B (en) 2019-11-12

Family

ID=62724199

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711448735.0A Active CN108254038B (en) 2017-12-27 2017-12-27 A kind of crude oil storage tank oil-water interfaces data go the calculation method of puppet and level gauging

Country Status (1)

Country Link
CN (1) CN108254038B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110987113A (en) * 2018-10-02 2020-04-10 通用汽车环球科技运作有限责任公司 Fuel level display filtering algorithm adjustment to prevent display of fuel depletion on meter
CN113688922A (en) * 2021-08-31 2021-11-23 西南石油大学 Fluid type identification method of agglomeration clustering unsupervised algorithm
CN116132483A (en) * 2023-02-24 2023-05-16 上海应用技术大学 Intelligent video detection method for interface identification

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6918296B1 (en) * 2004-03-04 2005-07-19 Delphi Technologies, Inc. Method of measuring fluid phases in a reservoir
JP2017021001A (en) * 2015-07-07 2017-01-26 株式会社日本自動車部品総合研究所 Liquid level detector
CN106840312A (en) * 2017-01-10 2017-06-13 陕西科技大学 A kind of crude oil storage tank water liquid level measurement mechanism for oil and method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6918296B1 (en) * 2004-03-04 2005-07-19 Delphi Technologies, Inc. Method of measuring fluid phases in a reservoir
JP2017021001A (en) * 2015-07-07 2017-01-26 株式会社日本自動車部品総合研究所 Liquid level detector
CN106840312A (en) * 2017-01-10 2017-06-13 陕西科技大学 A kind of crude oil storage tank water liquid level measurement mechanism for oil and method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
任喜伟 等: "电磁场式油水界面测量分析及数据优化方法", 《化工自动化及仪表》 *
刘远红 等: "k-means聚类算法在油水界面检测中的应用", 《化工自动化及仪表》 *
杨帆 等: "一种分布式原油储罐油水界面监测系统设计", 《计算机测量与控制》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110987113A (en) * 2018-10-02 2020-04-10 通用汽车环球科技运作有限责任公司 Fuel level display filtering algorithm adjustment to prevent display of fuel depletion on meter
CN113688922A (en) * 2021-08-31 2021-11-23 西南石油大学 Fluid type identification method of agglomeration clustering unsupervised algorithm
CN113688922B (en) * 2021-08-31 2023-07-25 西南石油大学 Fluid type identification method of condensation clustering unsupervised algorithm
CN116132483A (en) * 2023-02-24 2023-05-16 上海应用技术大学 Intelligent video detection method for interface identification

Also Published As

Publication number Publication date
CN108254038B (en) 2019-11-12

Similar Documents

Publication Publication Date Title
CN110634080B (en) Abnormal electricity utilization detection method, device, equipment and computer readable storage medium
Murcio et al. Multifractal to monofractal evolution of the London street network
CN108254038B (en) A kind of crude oil storage tank oil-water interfaces data go the calculation method of puppet and level gauging
CN104063588B (en) Multi-source data fusion-based method for predicting pipeline corrosion defect size
CN102855634B (en) Image detection method and image detection device
CN110929939B (en) Landslide hazard susceptibility spatial prediction method based on clustering-information coupling model
CN108154173B (en) Device and method for measuring oil-water interface of crude oil storage tank
CN110287975B (en) Flotation dosing abnormity detection method based on NSST morphological characteristics and depth KELM
CN105760673B (en) A kind of fluvial depositional reservoir seismic-sensitive parameterized template analysis method
CN108968811A (en) A kind of object identification method and system of sweeping robot
CN102393881B (en) A kind of high-precision detecting method of real-time many sensing temperatures data fusion
CN105180850B (en) Calculate the method and device of Maize Leaf leaf blight lesion area ratio
CN109541172A (en) The calculation method and device of soil attribute value
CN108764375B (en) Highway goods stock transprovincially matching process and device
CN102576370B (en) System and method for lacunarity analysis
CN112348290B (en) River water quality prediction method, river water quality prediction device, storage medium and storage device
CN113705931B (en) Method for predicting runoff elements by using K nearest neighbor method
CN115824993B (en) Method and device for determining water body chemical oxygen demand, computer equipment and medium
CN108896996B (en) A kind of Pb-Zn deposits absorbing well, absorption well water sludge interface ultrasonic echo signal classification method based on random forest
CN114387332B (en) Pipeline thickness measuring method and device
CN104268408A (en) Energy consumption data macro-forecast method based on wavelet coefficient ARMA model
CN117040983B (en) Data sharing method and system based on big data analysis
CN107358019A (en) Suitable for the commending system and method for the medical scheme of concept drift
CN117408167A (en) Debris flow disaster vulnerability prediction method based on deep neural network
CN110907015B (en) Liquid level monitoring method based on RFID (radio frequency identification) in indoor environment

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