CN109114431A - A kind of oil and gas pipeline hydrate monitoring technology - Google Patents
A kind of oil and gas pipeline hydrate monitoring technology Download PDFInfo
- Publication number
- CN109114431A CN109114431A CN201811155884.2A CN201811155884A CN109114431A CN 109114431 A CN109114431 A CN 109114431A CN 201811155884 A CN201811155884 A CN 201811155884A CN 109114431 A CN109114431 A CN 109114431A
- Authority
- CN
- China
- Prior art keywords
- sample
- deep learning
- inhibitor concentration
- oil
- learning model
- 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.)
- Pending
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D3/00—Arrangements for supervising or controlling working operations
- F17D3/01—Arrangements for supervising or controlling working operations for controlling, signalling, or supervising the conveyance of a product
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Pipeline Systems (AREA)
Abstract
The invention discloses a kind of oil and gas pipeline hydrate monitoring technology.The present invention includes: the acquisition and pretreatment of deep learning training data;Training deep learning model;It is predicted using metrical information.The present invention proposes a kind of physical parameter using trained deep learning model according to the collecting sample of physical parameter in transport pipeline and known inhibitor concentration and reasonable inhibitor concentration, it provides and further suppresses the transport pipeline hydrate monitoring method that dosage is suggested in agent, this method overcome the prior art as exploitation situation limitation and caused by it is at high cost, it is difficult to the defect of implementation;Overcome the shortcomings of to have proposed a kind of oil and gas pipeline hydrate monitoring technology that can further suppress agent dosage that method inhibits due to caused by calibrated shot chemical reagent gas hydrate synthesis effect unstable and proposed, it is a kind of convenient to carry out, transport pipeline hydrate monitoring method at low cost, with a high credibility.
Description
Technical field
The invention belongs to natural gases, Petroleum transport security field, are related to a kind of oil and gas pipeline hydrate monitoring technology.
Technical background
With society and its expanding economy, demand of each industry to industrialization and mechanization is increasingly promoted.Therefore, alive
Within the scope of boundary, to the demand of the energy also cumulative year after year.Natural gas, petroleum, as main energy sources, demand gradually expands,
International Energy Agency is in its Annual Research Report " world energy outlook ", it is expected that by emerging nation's such as the nations of China and India petrochemical industry
Additionally increase within 25 years with the drive of transportation until global crude oil consumption figure in 2035 is estimated to be up to daily 1.01 hundred million barrels
Daily 14,000,000 barrels, increase by 1,300,000 barrels again for estimated daily 99,700,000 barrels compared with last year.Therefore, the production of petroleum, transportation safety are asked
Topic is always worldwide hot issue.
In recent years, the transport pipeline between oil and gas exploitation ground and grown place is usually laid on deepwater regions.Just
The crude oil produced is mixture, wherein including other substances such as a large amount of gas, natural gas and water, paraffin.Meanwhile deepwater regions
Has the characteristics that low temperature, high pressure, such characteristic makes the substance in transport pipeline be easy to condense into nucleus, and the formation of nucleus can make
Hydrate quickly agglomerates, and finally blocks transport pipeline, and rupture transport pipeline, produces to world economy, environment, personal safety etc.
Grave danger has been given birth to, loss of the number in terms of billions of dollars can be caused every year through statistics Hydrate Plugging.Therefore, transport pipeline is kept
It is unobstructed become petroleum, natural gas production, transportation development key.
The prior art generallys use the method for the condition for inhibiting easily to be formed hydrate and the method drop of quantitative injecting inhibitor
The risk that lower hydrate generates.(1) method for inhibiting the easily condition of formation hydrate such as, passes through the method heated to pipeline and inhibits
The low temperature of deepwater regions;It is mixed into desiccant, such as ethylene glycol reduces the content of water in transport pipeline;Increase conduit cross-sectional area,
To achieve the purpose that reduce pressure.(2) method of injecting inhibitor, since the formation of nucleus and the degree of ionization etc. of solution are more
Kind factor is related, and therefore, can be able to suppress solution degree of ionization by the way that alcohol reagent is added and salt is added can increase solution
The method of degree of ionization is to achieve the purpose that nucleus is inhibited to be formed.There are many defects for the above method, such as: (1) passing through physics side
It is huge that method inhibits to be formed the condition of hydrate its cost, is unfavorable for the realization of industrialization;(2) due to exploitation the limitation in space,
Physics suppressing method is difficult to carry out;(3) concrete condition of the inhibition of chemical reagent usually with reagent dosage and transport pipeline has
It closes, the injection of quantitative inhibitor is difficult to meet the pipe condition of real-time change, and environment is polluted in the injection of excessive chemical reagent, together
When increase the cost of later period separation, and very few chemical reagent is difficult to play the role of to inhibit gas hydrate synthesis;(4) traditional skill
Art is only capable of theoretically inhibiting the formation of hydrate, it is difficult to after the case where judging transport pipeline and injection chemical reagent
The truth of pipeline.
It is therefore proposed that a kind of can provide chemical reagent reasonable volume, delivery tube convenient to carry out, at low cost, with a high credibility
Road hydrate monitoring method is of great significance to the development of energy industry.
Summary of the invention
The purpose of the invention is to realize that the safety corridor of petroleum, natural gas transports, overcome the prior art due to exploitation
Situation limitation and caused by it is at high cost, it is difficult to the defect of implementation;The method of having proposed is overcome to be made by calibrated shot chemical reagent
At the unstable deficiency of inhibition gas hydrate synthesis effect and a kind of dosage that can provide reasonable chemical reagent for proposing, convenient for real
It applies, transport pipeline hydrate monitoring method at low cost, with a high credibility.
The present invention proposes that a kind of physical message using trained deep learning models coupling pipeline provides further
Inhibitor suggests that the transport pipeline hydrate monitoring method of dosage, this method have spy convenient to carry out, at low cost, with a high credibility
Point.
The present invention is implemented as follows:
The acquisition and pretreatment of deep learning training data;
Training deep learning model;
It is predicted using metrical information.
Optionally, the acquisition Yu pretreatment of deep learning training data include: physical parameter and survey in measurement transport pipeline
Measure the physical parameter of the collecting sample of known inhibitor concentration and reasonable inhibitor concentration.
Physical parameter includes: to be utilized respectively pressure in above-mentioned measurement transport pipeline, and temperature sensor acquires in transport pipeline
Pressure, temperature information.
Inhibitor concentration known to above-mentioned measurement and the physical parameter of the collecting sample of reasonable inhibitor concentration include: that will acquire
To sample be put into sample storehouse, temperature sensor, conductivity sensor, the transmitting of sound wave, reception device are equipped in sample storehouse.It is logical
Transmitting, the reception device for crossing sound wave can measure speed of the sound wave by sample, pass through temperature sensor, conductivity sensor
Measurement, the temperature information of collecting sample and conductivity information respectively.
Optionally, above-mentioned trained deep learning model includes: with physical parameter in transport pipeline and known inhibitor concentration
Physical parameter with the collecting sample of reasonable inhibitor concentration is as inputting, with practical inhibitor concentration and reasonable inhibitor concentration
Extent of deviation as input training deep learning model.
Above-mentioned deep learning model is based on improved Artificial Neural Network Structures, using long memory network in short-term
(LSTM) structure can carry out feature extraction to input automatically, and output layer is using one-hot form according to input information to inhibitor
It is recommended that dosage is predicted.
Detailed description of the invention
Fig. 1 is a kind of foundation of transport pipeline hydrate monitoring method of the present invention, work flow diagram;
Fig. 2 is that a kind of transport pipeline hydrate monitoring method of the present invention measures known inhibitor concentration and reasonable inhibitor is dense
The physical parameter schematic diagram of device of the collecting sample of degree;
Fig. 3 is a kind of transport pipeline hydrate monitoring method parameter measuring apparatus connection figure of the present invention;
Fig. 4 is a kind of transport pipeline hydrate monitoring method deep learning model structure of the present invention;
Fig. 5 is a kind of transport pipeline hydrate monitoring method one-hot schematic diagram of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Not
It is detached from the case of the principle of the present invention, variation, modification, replacement and deformation is made to the embodiment of the present invention and belong to protection of the present invention
Range.
The embodiment of the invention provides a kind of transport pipeline hydrate monitoring methods, as shown in Figure 1, which comprises
The acquisition and pretreatment of S1, deep learning training data.
Specifically, being divided into adopting for physical parameter and known inhibitor concentration and reasonable inhibitor concentration in measurement transport pipeline
Collect the physical parameter of sample.
(1) physical parameter in the transport pipeline of known condition is measured.
Specifically, physical parameter includes: to utilize pressure, temperature sensor acquisition transport pipeline in above-mentioned measurement transport pipeline
Interior pressure, temperature information.Optionally, the embodiment of the present invention is utilized respectively platinum resistance sensor and petroleum pipeline pressure
Sensor acquires the temperature and pressure information inside pipeline respectively.
(2) physical parameter of the collecting sample of known inhibitor concentration and reasonable inhibitor concentration is measured.
Specifically, its survey of the physical parameter of the collecting sample of inhibitor concentration known to above-mentioned measurement and reasonable inhibitor concentration
Amount apparatus structure is as shown in Fig. 2, the conductivity of the main sample for measuring known inhibitor concentration situation, temperature, sound wave pass through sample
This speed.1 is sound wave generating device in figure, and 2 be sound wave receiving device, and 3 be sample storehouse, and 4 be conductivity measuring apparatus, and 5 are
Temperature detecting module.Its connecting structure is as shown in figure 3, sound wave R-T unit is sound wave generating device and acoustic receiver device in figure
General name.Host computer or chip controls single-chip microcontroller successively driving temperature detection module, conductivity measuring apparatus and sound wave R-T unit,
Each device, which believes the correlation being collected into, is transferred to host computer or chip, is stored, is analyzed.Due to the degree of ionization of solution
It is highly relevant with the formation of hydrate, and inhibitor inhibits the formation of hydrate in the method for controlling solution degree of ionization, therefore
It can quantify the degree of ionization of solution by way of measuring electrical conductivity of solution to predict, suggest inhibitor concentration.Due to solution
Ionic product is affected by temperature larger, therefore temperature is also used as one of main feature value to measure by the present invention.
Above-mentioned measurement sound wave, which mainly passes through sound wave R-T unit by the speed of sample, to carry out.It is penetrated since ultrasonic wave has
Property it is strong, directionality is preferable, can penetrate opaque substance characteristic, therefore sound wave R-T unit of the invention use ultrasonic transmission/reception
Device, ultrasonic frequency of the present invention use 1MHZ.Host computer or chip record ultrasonic receiving device issue and receive ultrasonic wave
Time difference.Since the width of sample storehouse is fixed and it is known that therefore can use the width calculating of above-mentioned time difference and sample storehouse
The speed that ultrasonic wave passes through sample.Shown in calculation method such as formula (1).
In formula: v be speed of the ultrasonic wave by sample, l be sample storehouse width, Δ t be ultrasonic receiving device issue and
Receive the time difference of ultrasonic wave.
Through the above method, corresponding information has been obtained: the pressure, temperature information of physical parameter in transport pipeline;Known inhibition
The speed that the conductivity of the collecting sample of agent concentration and reasonable inhibitor concentration, temperature, sound wave pass through sample.
S2, training deep learning model.
Specifically, the present invention uses improved neural network model, using LSTM neural network structure, structure such as Fig. 4
It is shown.
Wherein I1~InIt is specially pressure, temperature information in transport pipeline for the feature vector of input, it is known that inhibit
The speed that the conductivity of the collecting sample of agent concentration and reasonable inhibitor concentration, temperature, sound wave pass through sample;o1~onIt is trained
Label exports for target, is specially the suggestion dosage for further suppressing agent of one-hot label form, and one-hot form is former
Reason figure is as shown in Figure 5.I.e. each situation has a corresponding neuron, its correspondence neuron is activated defeated when that happens
It is out 1, other are 0.One-hot form label improves the robustness of deep learning model.Each layer of the model is adopted
With the mode connected entirely, shown in the calculation such as formula (2) between every layer.
Y=σ (wx+b) (2)
In formula: y is output, and σ is activation primitive, and w is parameter vector, and x is input vector, and b is bias vector.
Optionally, the above-mentioned activation primitive of the present invention uses ReLu function, shown in calculation method such as formula (3).
σ (z)=max (0, z) (3)
In formula, z is input, i.e. wx+b.
Optionally, the update of above-mentioned parameter vector of the present invention uses gradient descent method undated parameter.
Specifically, the training label of one-hot form, is the further suggestion to inhibitor dosage, it can be taking human as basis
The deviation of existing inhibitor concentration and optimal inhibitor concentration demarcates label, and such as currently it is recommended to increase 1 grade of inhibitor, suggestions to reduce
1 grade of inhibitor, current inhibitor is appropriate etc..It can be set according to demand according to the specific classification of extent of deviation.
Deep learning model of the present invention uses backpropagation techniques.Global ginseng is carried out according to the gradient of output layer cost function
Several optimization finally makes cost function reach minimum, even if output vector and object vector deviation are minimum.
S3, proof deep learning model.
The prediction degree of deep learning model need to be quantified, and output vector and object vector deviation answer minimum, therefore need
Cost function is wanted to be measured.Cost function should have closer with object vector when output vector, and cost function is smaller and complete
The larger feature of office's gradient.Therefore, optionally, the present invention uses cross entropy cost function.Cross entropy cost function such as formula (5) institute
Show.
In formula: n is output vector number;Y is target output vector;X is reality output vector.
Cross entropy describes the similarity degree between two vectors, and global gradient is more excellent, can be instructed at a relatively high speed
Practice.It therefore, be cost function using cross entropy is a preferred embodiment, the cost function after other regularizations can also be used carries out
Optimization.S4, it is predicted using metrical information.
Specifically, being predicted using desired deep learning model has been reached.
Specifically, physical parameter and known inhibitor concentration and reasonable inhibitor are dense in the transport pipeline of acquisition unknown situation
The physical parameter of the collecting sample of degree.Acquisition method is identical as acquisition method in step S1.The information input depth that will be collected into
After learning model, the deep learning model, that is, exportable suggestion dosage for further suppressing agent.
The invention proposes a kind of using deep learning model to the further of the inhibitor for providing inhibition gas hydrate synthesis
It is recommended that dosage.Compared with the conventional method, invention further reduces the security risk of transport pipeline, implementation cost is reduced,
Working efficiency is improved, the reliability of measurement result is increased, has established certain base for petroleum, natural gas production, transportation development
Plinth.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and what is described in the above embodiment and the description is only the present invention
Principle and one of optimum embodiment, without departing from the spirit and scope of the present invention the present invention also have various change and
It improves, these changes and improvements are both fallen in protection scope.
Claims (5)
1. a kind of oil and gas pipeline hydrate monitoring technology, which comprises the steps of:
The acquisition and pretreatment of S1, deep learning training data;
S2, training deep learning model;
S3, proof deep learning model;
S4, it is predicted using metrical information;
The acquisition of above-mentioned deep learning training data and pretreatment include: in the transport pipeline for measure known condition physical parameter and
Measure the physical parameter of the collecting sample of known inhibitor concentration and reasonable inhibitor concentration;
Physical parameter includes: to be utilized respectively pressure in the transport pipeline of above-mentioned measurement known condition, temperature sensor acquisition transport
Pressure, temperature information in pipeline;
Inhibitor concentration known to above-mentioned measurement and the physical parameter of the collecting sample of reasonable inhibitor concentration include: will be collected
Sample is put into sample storehouse, is equipped with temperature sensor, conductivity sensor, the transmitting of sound wave, reception device in sample storehouse;Pass through sound
The transmitting of wave, reception device can measure speed of the sound wave by sample, be distinguished by temperature sensor, conductivity sensor
Measurement, the temperature information of collecting sample and conductivity information;
Above-mentioned trained deep learning model includes: with pressure, the temperature information in transport pipeline, it is known that inhibitor concentration and rationally
The conductivity of the collecting sample of inhibitor concentration, temperature, sound wave by the speed of sample as input, one-hot form into
The suggestion dosage of one step inhibitor is as output training deep learning model;
It is above-mentioned using metrical information to pipe condition and required inhibitor situation carry out prediction include: system according to measured information from
Dynamic provide further suppresses agent suggestion dosage.
2. a kind of oil and gas pipeline hydrate monitoring technology as described in claim 1 is it is characterized by: utilize platinum resistance thermometer sensor,
Temperature sensor and petroleum pipeline pressure sensor acquire the temperature and pressure information inside pipeline respectively.
3. a kind of oil and gas pipeline hydrate monitoring technology as described in claim 1 is it is characterized by: pass through measurement solution
The degree of ionization of the form quantization solution of conductivity is to predict, suggest that inhibitor concentration, temperature are also used as one of main feature value
It measures.
4. a kind of oil and gas pipeline hydrate monitoring technology as described in claim 1 is it is characterized by: measurement sound wave passes through
The speed of sample mainly passes through sound wave R-T unit and carries out;Sound wave R-T unit uses ultrasonic receiving device;Host computer or core
Piece record ultrasonic receiving device issues and receives the time difference of ultrasonic wave;Because it is known that therefore the width of sample storehouse is fixed and
The width that can use above-mentioned time difference and sample storehouse calculates speed of the ultrasonic wave by sample;Shown in calculation method such as formula (1):
In formula: v is speed of the ultrasonic wave by sample, and l is sample storehouse width, and Δ t is that ultrasonic receiving device is issued and received
The time difference of ultrasonic wave.
5. a kind of oil and gas pipeline hydrate monitoring technology as described in claim 1 is it is characterized by: the deep learning
Model is LSTM neural network, and the suggestion dosage for further suppressing agent in the form of one-hot utilizes cross entropy generation as output
Valence function updates global parameter as loss function, the method for gradient decline.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811155884.2A CN109114431A (en) | 2018-09-30 | 2018-09-30 | A kind of oil and gas pipeline hydrate monitoring technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811155884.2A CN109114431A (en) | 2018-09-30 | 2018-09-30 | A kind of oil and gas pipeline hydrate monitoring technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109114431A true CN109114431A (en) | 2019-01-01 |
Family
ID=64857575
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811155884.2A Pending CN109114431A (en) | 2018-09-30 | 2018-09-30 | A kind of oil and gas pipeline hydrate monitoring technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109114431A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639828A (en) * | 2019-03-01 | 2020-09-08 | 北京国双科技有限公司 | Information processing method and related equipment |
CN112413413A (en) * | 2020-11-20 | 2021-02-26 | 成都艾斯皮埃尔科技有限公司 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
CN114777033A (en) * | 2022-04-28 | 2022-07-22 | 大连理工大学 | Carbon dioxide pipeline transportation guarantee system and method applying recyclable inhibitor |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6028236A (en) * | 1997-11-25 | 2000-02-22 | Institut Francais Du Petrole | Process for slowing the growth and/or agglomeration of hydrates in a production effluent |
CN101097040A (en) * | 2007-07-24 | 2008-01-02 | 李向东 | Method for restraining gas hydrate in natural gas pipe line and device thereof |
RU2372553C1 (en) * | 2008-05-05 | 2009-11-10 | Вадим Геннадьевич Некрасов | Device for transportation of gas and gas condensate in system well-gas pipeline (trail) |
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 |
CN104373821A (en) * | 2014-11-21 | 2015-02-25 | 天津科技大学 | Natural gas pipeline safety monitoring device based on acoustical science active spurring |
CN105443988A (en) * | 2015-11-13 | 2016-03-30 | 海洋石油工程股份有限公司 | Blockage relieving method for natural gas hydrate blocking in oil-gas mixing transportation pipeline |
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 |
CN107622427A (en) * | 2016-07-13 | 2018-01-23 | 阿里巴巴集团控股有限公司 | The method, apparatus and system of deep learning |
-
2018
- 2018-09-30 CN CN201811155884.2A patent/CN109114431A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6028236A (en) * | 1997-11-25 | 2000-02-22 | Institut Francais Du Petrole | Process for slowing the growth and/or agglomeration of hydrates in a production effluent |
CN101097040A (en) * | 2007-07-24 | 2008-01-02 | 李向东 | Method for restraining gas hydrate in natural gas pipe line and device thereof |
RU2372553C1 (en) * | 2008-05-05 | 2009-11-10 | Вадим Геннадьевич Некрасов | Device for transportation of gas and gas condensate in system well-gas pipeline (trail) |
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 |
CN104373821A (en) * | 2014-11-21 | 2015-02-25 | 天津科技大学 | Natural gas pipeline safety monitoring device based on acoustical science active spurring |
CN105443988A (en) * | 2015-11-13 | 2016-03-30 | 海洋石油工程股份有限公司 | Blockage relieving method for natural gas hydrate blocking in oil-gas mixing transportation pipeline |
CN107622427A (en) * | 2016-07-13 | 2018-01-23 | 阿里巴巴集团控股有限公司 | The method, apparatus and system of deep learning |
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 (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639828A (en) * | 2019-03-01 | 2020-09-08 | 北京国双科技有限公司 | Information processing method and related equipment |
CN111639828B (en) * | 2019-03-01 | 2023-08-29 | 北京国双科技有限公司 | Information processing method and related equipment |
CN112413413A (en) * | 2020-11-20 | 2021-02-26 | 成都艾斯皮埃尔科技有限公司 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
CN112413413B (en) * | 2020-11-20 | 2022-03-01 | 成都艾斯皮埃尔科技有限公司 | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology |
CN114777033A (en) * | 2022-04-28 | 2022-07-22 | 大连理工大学 | Carbon dioxide pipeline transportation guarantee system and method applying recyclable inhibitor |
CN114777033B (en) * | 2022-04-28 | 2024-06-11 | 大连理工大学 | Carbon dioxide pipeline transportation guarantee system and method applying recyclable inhibitor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106950347B (en) | A method of evaluation mud shale each group partial volume | |
CN109114431A (en) | A kind of oil and gas pipeline hydrate monitoring technology | |
CN103233704A (en) | Method and device for simulating experiment of permafrost region natural gas hydrate mining through replacement of CO2/N2 | |
Panthi et al. | Saltwater intrusion into coastal aquifers in the contiguous United States—a systematic review of investigation approaches and monitoring networks | |
CN103967478B (en) | A kind of peupendicular hole meteor trail echoes method based on conducting probe | |
CN110242865A (en) | A kind of gas leakage detection determination method and system being easy to Continuous optimization | |
Dai et al. | A simulation approach for shale gas development in China with embedded discrete fracture modeling | |
CN107795320A (en) | A kind of computational methods of horizontal well carbonate reservoir parameter | |
CN110162851A (en) | A kind of data calibration method of cable formation testing pumping numerical simulation and its process | |
Wang et al. | Calculation model and rapid estimation method for coal seam gas content | |
Huang et al. | A deep learning framework based on improved self‐supervised learning for ground‐penetrating radar tunnel lining inspection | |
Revil et al. | Induced polarization as a tool to assess alteration in geothermal systems: a review | |
CN203214026U (en) | Experimental simulation device for CO2/N2 displacement exploitation of natural gas hydrate in cryolithozone | |
Purbey et al. | Machine learning and data mining assisted petroleum reservoir engineering: a comprehensive review | |
Yue et al. | Leakage risk evaluation model for single wells of CO2: a case study | |
Wang et al. | Determine level of thief zone using fuzzy ISODATA clustering method | |
Lei et al. | Characterization of multiphase flow in shale oil reservoirs considering multiscale porous media by high-resolution numerical simulation | |
Cui et al. | Suggestions on the development of environmental monitoring technology of CO2 geological storage and leakage under the background of China’s “Double-Carbon” strategy | |
Yu et al. | Application of ant colony clustering algorithm in coal mine gas accident analysis under the background of big data research | |
CN103473894A (en) | Earthquake monitoring and early warning system and working method thereof | |
Liu et al. | Study of roof water inrush forecasting based on EM-FAHP two-factor model | |
CN104265259A (en) | Capacity tracking and evaluating method | |
Jun et al. | A new dynamic assessment for multi-parameters information of water inrush in coal mine | |
Stone et al. | Model documentation for relations between continuous real-time and discrete water-quality constituents in Cheney Reservoir near Cheney, Kansas, 2001--2009 | |
CN113702598A (en) | Building block type coal-series gas migration enrichment analysis experiment system and method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190101 |
|
WD01 | Invention patent application deemed withdrawn after publication |