CN108952637A - A kind of underwater tree security system and suppressing method for the inhibition of deepwater work hydrate - Google Patents
A kind of underwater tree security system and suppressing method for the inhibition of deepwater work hydrate Download PDFInfo
- Publication number
- CN108952637A CN108952637A CN201810722730.0A CN201810722730A CN108952637A CN 108952637 A CN108952637 A CN 108952637A CN 201810722730 A CN201810722730 A CN 201810722730A CN 108952637 A CN108952637 A CN 108952637A
- Authority
- CN
- China
- Prior art keywords
- inhibitor
- hydrate
- injection valve
- thermodynamic
- tree
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000005764 inhibitory process Effects 0.000 title claims description 7
- 239000003112 inhibitor Substances 0.000 claims abstract description 125
- 238000002347 injection Methods 0.000 claims abstract description 57
- 239000007924 injection Substances 0.000 claims abstract description 57
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 210000002569 neuron Anatomy 0.000 claims description 17
- 239000000126 substance Substances 0.000 claims description 11
- 239000007864 aqueous solution Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 239000003795 chemical substances by application Substances 0.000 claims description 2
- 230000009977 dual effect Effects 0.000 claims description 2
- 230000005284 excitation Effects 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 abstract description 13
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000012549 training Methods 0.000 description 11
- MTHSVFCYNBDYFN-UHFFFAOYSA-N diethylene glycol Chemical compound OCCOCCO MTHSVFCYNBDYFN-UHFFFAOYSA-N 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- NMJORVOYSJLJGU-UHFFFAOYSA-N methane clathrate Chemical compound C.C.C.C.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O NMJORVOYSJLJGU-UHFFFAOYSA-N 0.000 description 5
- 238000003786 synthesis reaction Methods 0.000 description 5
- LYCAIKOWRPUZTN-UHFFFAOYSA-N Ethylene glycol Chemical compound OCCO LYCAIKOWRPUZTN-UHFFFAOYSA-N 0.000 description 3
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003345 natural gas Substances 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010899 nucleation Methods 0.000 description 2
- 230000006911 nucleation Effects 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 235000013855 polyvinylpyrrolidone Nutrition 0.000 description 2
- 229920000036 polyvinylpyrrolidone Polymers 0.000 description 2
- 239000001267 polyvinylpyrrolidone Substances 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- JWYVGKFDLWWQJX-UHFFFAOYSA-N 1-ethenylazepan-2-one Chemical compound C=CN1CCCCCC1=O JWYVGKFDLWWQJX-UHFFFAOYSA-N 0.000 description 1
- LFCYHAXVBWPGQR-UHFFFAOYSA-N 2-propyl-4,5-dihydro-1h-imidazole Chemical compound CCCC1=NCCN1 LFCYHAXVBWPGQR-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 150000001298 alcohols Chemical class 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- SUPCQIBBMFXVTL-UHFFFAOYSA-N ethyl 2-methylprop-2-enoate Chemical compound CCOC(=O)C(C)=C SUPCQIBBMFXVTL-UHFFFAOYSA-N 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 150000002466 imines Chemical class 0.000 description 1
- 125000001449 isopropyl group Chemical group [H]C([H])([H])C([H])(*)C([H])([H])[H] 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 229920000098 polyolefin Polymers 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 239000011780 sodium chloride Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000004781 supercooling Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/01—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells specially adapted for obtaining from underwater installations
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B41/00—Equipment or details not covered by groups E21B15/00 - E21B40/00
- E21B41/0099—Equipment or details not covered by groups E21B15/00 - E21B40/00 specially adapted for drilling for or production of natural hydrate or clathrate gas reservoirs; Drilling through or monitoring of formations containing gas hydrates or clathrates
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/04—Measuring depth or liquid level
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/06—Measuring temperature or pressure
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/06—Measuring temperature or pressure
- E21B47/07—Temperature
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The present invention discloses a kind of underwater tree security system inhibited for deepwater work hydrate, comprising: inhibitor decanting point, between tree axial direction spaced set is set under water under water；First injection valve is arranged at the inhibitor decanting point, for injecting thermodynamic inhibitor；Second injection valve is arranged at the inhibitor decanting point, for injecting kinetic inhibitor；Winch is connected with the underwater tree, is axially moved for controlling the underwater tree along down-hole string, so that the inhibitor decanting point covers entire down-hole string.Multiple spot monitoring can be carried out to underwater tubing string, reach efficient hydrate and inhibit.Invention additionally discloses a kind of safe suppressing methods of tree under water inhibited for deepwater work hydrate, the unlatching of the first injection valve and the second injection hair and the addition depth of inhibitor are determined based on BP neural network, it also can control the additional amount of thermodynamic inhibitor and kinetic inhibitor, effectively inhibit the formation of hydrate.
Description
Technical field
The present invention relates to marine deep water petroleum, natural gas exploration technical field, and more particularly, the present invention relates to a kind of use
In the underwater tree security system and suppressing method of the inhibition of deepwater work hydrate.
Background technique
The petroleum on stratum, natural gas are led into ground when current technology status is operation and carry out data recording.But in stone
During oily natural gas leads to ground, since the variation of pressure, temperature, especially sea bed are nearby close to the sea water temperature of zero degree
Degree easily to form hydrate in tubing string, and hydrate cracking can cause the damage or blocking of oil pipe once being formed, to entire
The safety of job platform threatens, and huge exploration investment is by all that has been achieved is spoiled.
Existing pipe string technology is unable to monitor the temperature change of petroleum gas, can not inject hydrate inhibitor, be only capable of
In case of emergency closed safe valve.But once tubing string pierces leakage below safety-valve, and safety-valve can not also ensure safety,
It is exposed to entire operation among danger.
It can be changed by apparent temperature and pressure when hydrate is formed in oil pipe according to the study, formation initial stage is optimal inhibition point,
But existing technology is unable to monitor data variation, misses the best period of inhibition, leaves safely to deep water test jobs huge
Big hidden danger.
Summary of the invention
It is an object of the invention to design and develop a kind of underwater tree safety system inhibited for deepwater work hydrate
System can carry out multiple spot monitoring to underwater tubing string, reach efficient hydrate and inhibit.
Another object of the present invention is to have designed and developed a kind of underwater tree safety inhibited for deepwater work hydrate
Suppressing method determines the unlatching of the first injection valve and the second injection hair and the addition depth of inhibitor based on BP neural network,
Efficiently inhibit gas hydrate synthesis.
The present invention can also control thermodynamic inhibitor and power according to the open state of the first injection valve and the second injection valve
The additional amount of inhibitor is learned, the formation of hydrate is effectively inhibited.
Technical solution provided by the invention are as follows:
A kind of underwater tree security system inhibited for deepwater work hydrate, comprising:
Inhibitor decanting point, between tree axial direction spaced set is set under water under water；
First injection valve is arranged at the inhibitor decanting point, for injecting thermodynamic inhibitor；
Second injection valve is arranged at the inhibitor decanting point, for injecting kinetic inhibitor；
Winch is connected with the underwater tree, is axially moved for controlling the underwater tree along down-hole string, so that described
Inhibitor decanting point covers entire down-hole string.
Preferably, further includes:
Temperature sensor is set in qually spaced at the down-hole string inner wall, outside wall surface and sea bed mud face, is used for
Detect temperature；
Pressure sensor is separately positioned at the temperature sensor, for detecting pressure；
Depth transducer is separately positioned at the temperature sensor, for detecting depth；
Controller is connect with the temperature sensor, pressure sensor, the first injection valve, the second injection valve and winch,
For receive the detection data of the temperature sensor and pressure sensor and control first injection valve, the second injection valve and
Winch work.
Correspondingly, the present invention also provides it is a kind of for deepwater work hydrate inhibit the safe suppressing method of tree under water, when
When carrying out underground work, the addition depth and the first injection valve and the second injection valve of inhibitor are determined based on BP neural network
State includes the following steps:
Step 1: according to the sampling period, passing through sensor measurement down-hole string internal temperature and pressure, external temperature and pressure
Temperature and pressure at power and sea bed mud face；
Step 2: determining the input layer vector x={ x of three layers of BP neural network1,x2,x3,x4,x5,x6}；Wherein,
x1For down-hole string internal temperature, x2For down-hole string internal pressure, x3For down-hole string external temperature, x4Outside for down-hole string
Portion's temperature, x5For temperature at sea bed mud face, x6For pressure at sea bed mud face；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING to middle layer, the neuron of middle layer are m；
Step: 4: obtaining output layer neuron vector o={ o1,o2,o3}；Wherein, o1For the state of the first injection valve, o2For
The state of second injection valve, o3For the addition depth of inhibitor, the output layer neuron value isK is output layer mind
Through metasequence number, k={ 1,2 } works as okWhen being 1, injection valve is in the open state, works as okWhen being 0, injection valve is in close state.
Preferably, the middle layer node number m meets:Wherein n is input layer
Number, p are output layer node number.
Preferably, the excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
Preferably, work as o1=1, o2When=0, the amount of thermodynamic inhibitor is controlled are as follows:
Wherein, mt0For the amount of the thermodynamic inhibitor when inhibitor only has thermodynamic inhibitor, ρ is the density of water, and Δ T is
The temperature drop of hydrate is formed, α is concentration and thermodynamic inhibitor of the thermodynamic inhibitor in substance to be collected in aqueous solution
In the ratio between concentration, M is the molecular weight of thermodynamic inhibitor, and K is constant, and Q is the flow of substance to be collected in tubing string, and C is heat
The molar concentration of mechanics inhibitor, π are pi, and r is tubing string internal diameter, and l is the area that thermodynamic inhibitor is added in tubing string and influences
Domain height.
Preferably, work as o1=0, o2When=1, the amount of control dynamics inhibitor are as follows:
Wherein, md0For the amount of the kinetic inhibitor when inhibitor only has kinetic inhibitor, ρ is the density of water, and π is circle
Frequency, r are tubing string internal diameter, and l is the region height that kinetic inhibitor is added in tubing string and influences.
Preferably, work as o1=1, o2When=1, the amount for controlling thermodynamic inhibitor and kinetic inhibitor is respectively as follows:
Wherein, mt1For the amount of thermodynamic inhibitor in inhibitor, md1For the amount of kinetic inhibitor in inhibitor, ρ is water
Density, Δ T is the temperature drop to form hydrate, and α is concentration of the thermodynamic inhibitor in substance to be collected and thermodynamics suppression
The ratio between the concentration of preparation in aqueous solution, M are the molecular weight of thermodynamic inhibitor, and K is constant, and Q is substance to be collected in tubing string
Flow, C is the molar concentration of thermodynamic inhibitor, and π is pi, and r is tubing string internal diameter, and l is that inhibitor shadow is added in tubing string
Loud region height.
It is of the present invention the utility model has the advantages that
(1) the underwater tree security system of the present invention inhibited for deepwater work hydrate, can be to underwater tubing string
Multiple spot monitoring is carried out, reaches efficient hydrate and inhibits.
(2) the tree under water safe suppressing method of the present invention inhibited for deepwater work hydrate, based on BP nerve
Network determines the unlatching of the first injection valve and the second injection hair and the addition depth of inhibitor, efficiently inhibits gas hydrate synthesis.
The addition of thermodynamic inhibitor and kinetic inhibitor can also be controlled according to the open state of the first injection valve and the second injection valve
Amount effectively inhibits the formation of hydrate.
Detailed description of the invention
Fig. 1 is the schematic diagram for the underwater tree security system that deepwater work hydrate of the present invention inhibits.
Fig. 2 is the temperature, pressure phase curve that gas hydrate synthesis of the present invention simulation is checked.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, the present invention provides a kind of underwater tree security system inhibited for deepwater work hydrate, comprising:
Inhibitor decanting point, between tree axial direction spaced set is set under water under water；First injection valve is arranged in the inhibition
At agent decanting point, for injecting thermodynamic inhibitor；Second injection valve is arranged at the inhibitor decanting point, for infusing
Enter kinetic inhibitor；Winch is connected with the underwater tree, is axially moved for controlling the underwater tree along down-hole string,
So that the inhibitor decanting point covers entire down-hole string.Further include: temperature sensor is set in qually spaced in the underground
At pipe string internal wall face, outside wall surface and sea bed mud face, for detecting temperature；Pressure sensor is separately positioned on the temperature
At sensor, for detecting pressure；Depth transducer is separately positioned at the temperature sensor, for detecting depth；Control
Device (bottom surface electric-control board) processed, with the temperature sensor, pressure sensor, the first injection valve, the second injection valve and winch
Connection, for receiving the detection data of the temperature sensor and pressure sensor and controlling first injection valve, the second note
Enter valve and winch work.
The kinetic inhibitor is some water-soluble or aqueous dispersion polymers, they only inhibit hydrate in water phase
Formation, be added that concentration is very low (in water phase be usually less than 1%), it does not influence the thermodynamic condition of hydrate generation.In water
The initial stage of object crystallization nucleation and growth is closed, they are adsorbed in the surface of hydrate particle, and the cyclic structure of inhibitor passes through hydrogen bond
With the crystal combination of hydrate, delays the hydrate nucleation time or prevent the further growth of crystal to make in tubing string
Fluid flows under at a temperature below hydrate-formation temperature (i.e. in certain degree of supercooling), without there is Hydrate Plugging phenomenon,
Usually have PVP (polyvinylpyrrolidone), ethyl methacrylate, N- acyl group polyolefin imines, N- vinylcaprolactam,
N, N- alkyl acrylamide, poly- isopropyl acrylamide, 2- propyl -2- imidazoline etc..
The thermodynamic inhibitor, which then passes through to change, generates item to the thermodynamics of material to be mined, water and hydrate three-phase equilibrium
Part reduces the activity coefficient of water, causes to generate hydrate needs more High Voltage or lower temperature, in the temperature of general oil-gas pipeline
It is not easy to form hydrate under degree and pressure conditions.Thermodynamic inhibitor be mainly some alcohols (methanol, ethylene glycol, diethylene glycol (DEG)) with
And sodium chloride solution etc..
The underwater tree security system of the present invention inhibited for deepwater work hydrate, can carry out underwater tubing string
Multiple spot monitoring reaches efficient hydrate and inhibits.
The present invention also provides a kind of safe suppressing methods of tree under water inhibited for deepwater work hydrate, when progress underground
When operation, the addition depth of inhibitor and the state of the first injection valve and the second injection valve are determined based on BP neural network, are wrapped
Include following steps:
Step 1: establishing BP neural network model.
Totally interconnected connection is formed on BP model between the neuron of each level, is not connected between the neuron in each level
It connects, the output of input layer is identical as input, i.e. oi=xi.The operating characteristic of the neuron of intermediate hidden layer and output layer
Are as follows:
opj=fj(netpj)
Wherein p indicates current input sample, ωjiFor from neuron i to the connection weight of neuron j, opiFor neuron
The current input of j, opjIt is exported for it；fjFor it is non-linear can micro- non-decreasing function, be generally taken as S type function, i.e. fj(x)=1/ (1
+e-x)。
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding
Indicate that n detection signal of down-hole string, these signal parameters are provided by data preprocessing module；The second layer is that middle layer is (hidden
Layer), total m node is determined in an adaptive way by the training process of network；Third layer is output layer, total p node, by
System actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input vector: x=(x1,x2,...,xn)T
Middle layer vector: y=(y1,y2,...,ym)T
Output vector: o=(o1,o2,...,op)T
In the present invention, input layer number be n=6, output layer number of nodes be p=3, hidden layer number of nodes according toIt determines, m=5.
6 parameters of input layer respectively indicate are as follows: x1For down-hole string internal temperature, x2For down-hole string internal pressure, x3For
Down-hole string external temperature, x4For down-hole string external temperature, x5For temperature at sea bed mud face, x6For pressure at sea bed mud face；
3 parameters of output layer respectively indicate are as follows: o1For the state of the first injection valve, o2For the state of the second injection valve, o3For
The addition depth of inhibitor, the output layer neuron value areK be output layer neuron sequence number, k={ 1,2 },
Work as okWhen being 1, injection valve is in the open state, works as okWhen being 0, injection valve is in close state.
Step 2: carrying out the training of BP neural network.
After establishing BP neural network nodal analysis method, the training of BP neural network can be carried out.It is passed through according to the history of product
Test the sample of data acquisition training, and the connection weight between given input node i and hidden layer node j, hidden node j and defeated
Connection weight between node layer k out.
The acquisition of the historical empirical data is checked according to gas hydrate synthesis simulation and is determined, with specific reference to formation hydrate
Temperature and pressure determines depth locating for the position, needs to add the shape that inhibitor can effectively prevent hydrate at this location
At.The temperature and pressure for forming hydrate is as shown in table 1, and temperature, pressure phase curve is as shown in Figure 2.
The temperature and pressure of the formation hydrate of table 1
(1) training method
Each subnet is using individually trained method；When training, first have to provide one group of training sample, each of these sample
This, to forming, when all reality outputs of network and its consistent ideal output, is shown to train by input sample and ideal output
Terminate；Otherwise, by correcting weight, keep the ideal output of network consistent with reality output；Output sample when the training of each subnet
As shown in table 2.
The output sample of 2 network training of table
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can be concluded
It is as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum when being calculated for n-th,For l layers of j units with it is previous
Connection weight between the unit i of layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) unit i send
Working signal；When i=0, enableFor the threshold value of l layers of j unit.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
And ej(n)=xj(n)-oj(n)；
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training
Input sequence is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow etc.
Problem.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time shorter,
Network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe
Wherein J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector,
Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using
The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and
In the case where quantity, system can carry out self study, to constantly improve network performance.
When the state of the addition depth and the first injection valve and the second injection valve that determine inhibitor:
(1) work as o1=1, o2When=0, the amount of thermodynamic inhibitor is controlled are as follows:
Wherein, mt0For the amount (kg) of the thermodynamic inhibitor when inhibitor only has thermodynamic inhibitor, ρ is the density of water
(kg/m3), Δ T is the temperature drop (DEG C) to form hydrate, and α is concentration and heating power of the thermodynamic inhibitor in substance to be collected
The ratio between the concentration of inhibitor in aqueous solution is learned, M is the molecular weight (kg/mol) of thermodynamic inhibitor, and K is constant, and Q is tubing string
In substance to be collected flow (m3), C is the molar concentration (mol/m of thermodynamic inhibitor3), π is pi, and r is tubing string internal diameter
(m), l is the region height (m) that thermodynamic inhibitor is added in tubing string and influences.
(2) work as o1=0, o2When=1, the amount of control dynamics inhibitor are as follows:
Wherein, md0For the amount (kg) of the kinetic inhibitor when inhibitor only has kinetic inhibitor, ρ is the density of water
(kg/m3), π is pi, and r is tubing string internal diameter (m), and l is the region height (m) that kinetic inhibitor is added in tubing string and influences.
(3) work as o1=1, o2When=1, the amount for controlling thermodynamic inhibitor and kinetic inhibitor is respectively as follows:
Wherein, mt1For the amount (kg) of thermodynamic inhibitor in inhibitor, md1For the amount of kinetic inhibitor in inhibitor
(kg), ρ is the density (kg/m of water3), Δ T is the temperature drop (DEG C) to form hydrate, and α is thermodynamic inhibitor in object to be collected
The ratio between the concentration of concentration and thermodynamic inhibitor in aqueous solution in matter, M are the molecular weight (kg/mol) of thermodynamic inhibitor,
K is constant, and Q is the flow (m of substance to be collected in tubing string3), C is the molar concentration (mol/m of thermodynamic inhibitor3), π is circle
Frequency, r are tubing string internal diameter (m), and l is the region height (m) that inhibitor is added in tubing string and influences.
Below with reference to specific embodiment further to the water inhibited provided by the present invention for deepwater work hydrate
The lower safe suppressing method of tree is illustrated.
Underground work is simulated, 16 groups of different temperatures of simulation pressure corresponding with hydrate is formed is tested, specific number
According to as shown in table 3.
3 analogue data of table
According to the detection evaluation model principle of aforementioned foundation, the addition depth and the first injection valve and of inhibitor are determined
The state of two injection valves, conclusion are as shown in table 4.
Table 4 exports result
| Grouping | First injection valve | Second injection valve | Depth (m) is added in inhibitor |
| 1 | 0 | 1 | 500 |
| 2 | 0 | 1 | 550 |
| 3 | 0 | 1 | 600 |
| 4 | 0 | 1 | 650 |
| 5 | 1 | 0 | 700 |
| 6 | 1 | 0 | 750 |
| 7 | 1 | 0 | 800 |
| 8 | 1 | 0 | 850 |
| 9 | 1 | 0 | 900 |
| 10 | 1 | 1 | 950 |
| 11 | 1 | 1 | 1000 |
| 12 | 1 | 1 | 1100 |
| 13 | 1 | 1 | 1200 |
| 15 | 1 | 1 | 1300 |
| 15 | 1 | 1 | 1400 |
| 16 | 1 | 1 | 1500 |
And according to the amount of the inhibitor of above-mentioned determination be added inhibitor after carry out having seen whether hydrate generation, as a result such as
Shown in table 5.
5 hydrate of table generates result
| Grouping | Whether hydrate is formed |
| 1 | It is no |
| 2 | It is no |
| 3 | It is no |
| 4 | It is no |
| 5 | It is no |
| 6 | It is no |
| 7 | It is no |
| 8 | It is no |
| 9 | It is no |
| 10 | It is no |
| 11 | It is no |
| 12 | It is no |
| 13 | It is no |
| 15 | It is no |
| 15 | It is no |
| 16 | It is no |
As can be seen from Table 5, it is generated without hydrate, illustrates that the method effectively inhibits the generation of hydrate.
The tree under water safe suppressing method of the present invention inhibited for deepwater work hydrate, is based on BP neural network
It determines the unlatching of the first injection valve and the second injection hair and the addition depth of inhibitor, efficiently inhibits gas hydrate synthesis.It can also
The additional amount that thermodynamic inhibitor and kinetic inhibitor are controlled according to the open state of the first injection valve and the second injection valve, has
Effect inhibits the formation of hydrate.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (8)
1. a kind of underwater tree security system inhibited for deepwater work hydrate characterized by comprising
Inhibitor decanting point, between tree axial direction spaced set is set under water under water；
First injection valve is arranged at the inhibitor decanting point, for injecting thermodynamic inhibitor；
Second injection valve is arranged at the inhibitor decanting point, for injecting kinetic inhibitor；
Winch is connected with the underwater tree, is axially moved for controlling the underwater tree along down-hole string, so that the inhibition
Agent decanting point covers entire down-hole string.
2. the underwater tree security system inhibited as described in claim 1 for deepwater work hydrate, which is characterized in that also wrap
It includes:
Temperature sensor is set in qually spaced at the down-hole string inner wall, outside wall surface and sea bed mud face, for detecting
Temperature；
Pressure sensor is separately positioned at the temperature sensor, for detecting pressure；
Depth transducer is separately positioned at the temperature sensor, for detecting depth；
Controller connect with the temperature sensor, pressure sensor, the first injection valve, the second injection valve and winch, is used for
It receives the detection data of the temperature sensor and pressure sensor and controls first injection valve, the second injection valve and winch
Work.
3. a kind of safe suppressing method of tree under water inhibited for deepwater work hydrate, which is characterized in that when progress underground work
When industry, the addition depth of inhibitor and the state of the first injection valve and the second injection valve are determined based on BP neural network, including
Following steps:
Step 1: according to the sampling period, by sensor measurement down-hole string internal temperature and pressure, external temperature and pressure with
And temperature and pressure at sea bed mud face；
Step 2: determining the input layer vector x={ x of three layers of BP neural network1,x2,x3,x4,x5,x6}；Wherein, x1For well
Lower tubular column internal temperature, x2For down-hole string internal pressure, x3For down-hole string external temperature, x4For down-hole string external temperature,
x5For temperature at sea bed mud face, x6For pressure at sea bed mud face；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING to middle layer, the neuron of middle layer are m；
Step: 4: obtaining output layer neuron vector o={ o1,o2,o3}；Wherein, o1For the state of the first injection valve, o2It is second
The state of injection valve, o3For the addition depth of inhibitor, the output layer neuron value isK is output layer neuron
Sequence number, k={ 1,2 }, works as okWhen being 1, injection valve is in the open state, works as okWhen being 0, injection valve is in close state.
4. the safe suppressing method of tree under water inhibited as claimed in claim 3 for deepwater work hydrate, which is characterized in that
The middle layer node number m meets:Wherein n is input layer number, and p is output node layer
Number.
5. the safe suppressing method of tree under water inhibited as claimed in claim 4 for deepwater work hydrate, which is characterized in that
The excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
6. the safe suppressing method of tree under water inhibited for deepwater work hydrate as described in claim 3,4 or 5, feature
It is, works as o1=1, o2When=0, the amount of thermodynamic inhibitor is controlled are as follows:
Wherein, mt0For the amount of the thermodynamic inhibitor when inhibitor only has thermodynamic inhibitor, ρ is the density of water, and Δ T is to be formed
The temperature of hydrate drops, α be concentration and thermodynamic inhibitor of the thermodynamic inhibitor in substance to be collected in aqueous solution
The ratio between concentration, M are the molecular weight of thermodynamic inhibitor, and K is constant, and Q is the flow of substance to be collected in tubing string, and C is thermodynamics
The molar concentration of inhibitor, π are pi, and r is tubing string internal diameter, and l is the region height that thermodynamic inhibitor is added in tubing string and influences
Degree.
7. the safe suppressing method of tree under water inhibited for deepwater work hydrate as described in claim 3,4 or 5, feature
It is, works as o1=0, o2When=1, the amount of control dynamics inhibitor are as follows:
Wherein, md0For the amount of the kinetic inhibitor when inhibitor only has kinetic inhibitor, ρ is the density of water, and π is circumference
Rate, r are tubing string internal diameter, and l is the region height that kinetic inhibitor is added in tubing string and influences.
8. the safe suppressing method of tree under water inhibited for deepwater work hydrate as described in claim 3,4 or 5, feature
It is, works as o1=1, o2When=1, the amount for controlling thermodynamic inhibitor and kinetic inhibitor is respectively as follows:
Wherein, mt1For the amount of thermodynamic inhibitor in inhibitor, md1For the amount of kinetic inhibitor in inhibitor, ρ is the close of water
Degree, Δ T are the temperature drop to form hydrate, and α is concentration and thermodynamic inhibitor of the thermodynamic inhibitor in substance to be collected
The ratio between concentration in aqueous solution, M are the molecular weight of thermodynamic inhibitor, and K is constant, and Q is the stream of substance to be collected in tubing string
Amount, C are the molar concentration of thermodynamic inhibitor, and π is pi, and r is tubing string internal diameter, and l is to be added what inhibitor influenced in tubing string
Region height.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810722730.0A CN108952637B (en) | 2018-07-04 | 2018-07-04 | Underwater tree safety system and method for hydrate inhibition in deepwater operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810722730.0A CN108952637B (en) | 2018-07-04 | 2018-07-04 | Underwater tree safety system and method for hydrate inhibition in deepwater operation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108952637A true CN108952637A (en) | 2018-12-07 |
| CN108952637B CN108952637B (en) | 2020-08-14 |
Family
ID=64485531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810722730.0A Active CN108952637B (en) | 2018-07-04 | 2018-07-04 | Underwater tree safety system and method for hydrate inhibition in deepwater operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108952637B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109653730A (en) * | 2018-12-12 | 2019-04-19 | 中法渤海地质服务有限公司 | One kind being used for drill-stem test operation downhole perforation well section depth calibration method |
| CN110644977A (en) * | 2019-09-16 | 2020-01-03 | 中海艾普油气测试（天津）有限公司 | Control method for receiving and sending underground small signals for testing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100193194A1 (en) * | 2007-09-25 | 2010-08-05 | Stoisits Richard F | Method For Managing Hydrates In Subsea Production Line |
| CN103154424A (en) * | 2010-10-12 | 2013-06-12 | Bp北美公司 | Subsea free standing riser system and method |
| CN104198674A (en) * | 2014-08-29 | 2014-12-10 | 西南石油大学 | Pipeline natural gas hydrate formation online early-warning device and method |
| US8978767B2 (en) * | 2008-08-19 | 2015-03-17 | Onesubsea, Llc | Subsea well intervention lubricator and method for subsea pumping |
| CN106194165A (en) * | 2016-08-26 | 2016-12-07 | 中国石油大学(华东) | Gas hydrates blocking monitoring device and method in the test of deep water gas well |
| CN106322121A (en) * | 2016-08-26 | 2017-01-11 | 中国石油大学(华东) | Early monitoring device and method for hydrate blockage of deep water gas well production pipeline |
-
2018
- 2018-07-04 CN CN201810722730.0A patent/CN108952637B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100193194A1 (en) * | 2007-09-25 | 2010-08-05 | Stoisits Richard F | Method For Managing Hydrates In Subsea Production Line |
| US8978767B2 (en) * | 2008-08-19 | 2015-03-17 | Onesubsea, Llc | Subsea well intervention lubricator and method for subsea pumping |
| CN103154424A (en) * | 2010-10-12 | 2013-06-12 | Bp北美公司 | Subsea free standing riser system and method |
| CN104198674A (en) * | 2014-08-29 | 2014-12-10 | 西南石油大学 | Pipeline natural gas hydrate formation online early-warning device and method |
| CN106194165A (en) * | 2016-08-26 | 2016-12-07 | 中国石油大学(华东) | Gas hydrates blocking monitoring device and method in the test of deep water gas well |
| CN106322121A (en) * | 2016-08-26 | 2017-01-11 | 中国石油大学(华东) | Early monitoring device and method for hydrate blockage of deep water gas well production pipeline |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109653730A (en) * | 2018-12-12 | 2019-04-19 | 中法渤海地质服务有限公司 | One kind being used for drill-stem test operation downhole perforation well section depth calibration method |
| CN110644977A (en) * | 2019-09-16 | 2020-01-03 | 中海艾普油气测试（天津）有限公司 | Control method for receiving and sending underground small signals for testing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108952637B (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104895560B (en) | A kind of deep water test wellbore pressure, temperature field simulation and Hydrate Prediction method | |
| CN103226641B (en) | Coupling calculation method of deepwater gas-liquid two-phase flow circulating temperature and pressure | |
| Choobbasti et al. | Modeling and optimization of a trench layer location around a pipeline using artificial neural networks and particle swarm optimization algorithm | |
| BRPI0706805A2 (en) | computer readable methods, systems and media for rapid upgrade of oil and gas field production models with proxy and physical simulators | |
| Naseri et al. | Development of an accurate method to prognosticate choke flow coefficients for natural gas flow through nozzle and orifice type chokes | |
| CN105117511A (en) | Fracture-cavity reservoir inter-well communication passage and flow parameter characterization method | |
| WO2019242296A1 (en) | Method for obtaining relationship model between water injection well and oil production well, and method for determining production rate and water injection amount | |
| NO20101371A1 (en) | Method, system and apparatus for modeling uncertainty in production system networks | |
| NO20131298A1 (en) | Lifting and throat control | |
| Li et al. | Numerical modeling of fluid flow in tight oil reservoirs considering complex fracturing networks and Pre-Darcy flow | |
| Hazbeh et al. | Proposing a new model for estimation of oil rate passing through wellhead chokes in an Iranian heavy oil field | |
| CN102682195B (en) | Semisubmersible platform transient state bored shaft temperature computation method | |
| CN113947041A (en) | Shale reservoir fracturing network expansion flow integrated simulation method | |
| CN108952637A (en) | A kind of underwater tree security system and suppressing method for the inhibition of deepwater work hydrate | |
| CN104405368B (en) | Gas well at HTHP well-head pressure-measuring method for distinguishing adaptability | |
| CN112160734A (en) | Injection and production well correlation analysis method and device, storage medium and computer equipment | |
| Razi et al. | Annular pressure loss while drilling prediction with artificial neural network modeling | |
| Naderi et al. | Optimizing production from water drive gas reservoirs based on desirability concept | |
| Ji-Cheng et al. | Neural approach for calculating permeability of porous medium | |
| Elesin et al. | The inverse coefficient problem for equations of three-phase flow in porous medium | |
| Li et al. | Experimental and numerical investigation of Gas–Liquid gravity displacement in a horizontal well intersecting a vertical fracture | |
| Suleymanov et al. | Oil reservoir waterflooding efficiency evaluation method | |
| Rutagarama | The role of well testing in geothermal resource assessment | |
| Xie et al. | Transient simulation of the blowing-out process of the air pockets in vertical wellbore | |
| Paz et al. | Prediction of calcium carbonate scaling in pipes using artificial neural networks |
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 |