CN112016766A - Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network - Google Patents
Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network Download PDFInfo
- Publication number
- CN112016766A CN112016766A CN202010979086.2A CN202010979086A CN112016766A CN 112016766 A CN112016766 A CN 112016766A CN 202010979086 A CN202010979086 A CN 202010979086A CN 112016766 A CN112016766 A CN 112016766A
- Authority
- CN
- China
- Prior art keywords
- early warning
- overflow
- leakage
- drilling
- risk
- 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
- 238000005553 drilling Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000006403 short-term memory Effects 0.000 title claims abstract description 18
- 230000007787 long-term memory Effects 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 26
- 230000015654 memory Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 239000012530 fluid Substances 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000001902 propagating effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 18
- 239000007789 gas Substances 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011430 maximum method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention provides an oil and gas well drilling overflow and leakage early warning method based on a long-term and short-term memory network, which comprises the following steps: constructing an overflow and leakage risk early warning model based on a long and short term memory network, wherein the overflow and leakage risk early warning model comprises an input layer, a hidden layer and an output layer, and the hidden layer comprises at least two layers of long and short term memory network structures; training an overflow and leakage risk early warning model by using the existing drilling risk data; and (4) performing drilling and leakage early warning on the oil and gas well by using the trained leakage risk early warning model. The beneficial effects of the invention can include: the method can timely and accurately give out the identification result, can reduce the dependence of risk identification on prior knowledge and expert experience, enables the early warning of the drilling risk to be more intelligent and efficient, and has good field application prospect.
Description
Technical Field
The invention relates to the field of well control safety in petroleum and natural gas drilling engineering, in particular to an oil and gas well drilling overflow and leakage early warning method based on a long-term and short-term memory network.
Background
Overflow and well leakage are two risks which are easy to occur in the drilling process, and the overflow and leakage dangerous situation is easy to occur particularly in oil and gas exploration blocks with the characteristics of deep wells, ultra-deep wells, fault development, carbonate rocks and the like and newly opened blocks with some underground pressure systems which are not very clear. The overflow and the lost circulation not only can cause serious damage to a reservoir stratum, increase the development cost and reduce the development efficiency, but also can induce the drilling accidents such as drilling sticking, well collapse, blowout and the like once the control is not successful, thereby causing serious casualties and economic loss. Therefore, the real-time monitoring and early warning of early overflow and lost circulation in the drilling process is of great significance to safe and efficient drilling and drilling cost saving.
The drilling process is a complex nonlinear dynamic process, uncertainty factors are numerous, random interference on various drilling parameters is large, the parameters are correlated and coupled, an accurate overflow and leakage risk identification model is difficult to establish, and the accuracy of overflow and leakage early warning is limited.
Disclosure of Invention
In view of the deficiencies in the prior art, it is an object of the present invention to address one or more of the problems in the prior art as set forth above. For example, one of the objectives of the present invention is to improve the accuracy of the overflow monitoring and early warning.
In order to achieve the purpose, the invention provides an oil and gas well drilling overflow and leakage early warning method based on a long-term and short-term memory network. The early warning method can comprise the following steps: constructing an overflow and leakage risk early warning model based on a long and short term memory network, wherein the overflow and leakage risk early warning model comprises an input layer, a hidden layer and an output layer, and the hidden layer comprises at least two layers of long and short term memory network structures; training an overflow and leakage risk early warning model by using the existing drilling risk data; and (4) performing drilling and leakage early warning on the oil and gas well by using the trained leakage risk early warning model.
According to an exemplary embodiment of the present invention, the early warning method may include the steps of: constructing an overflow and leakage risk early warning model based on a long and short term memory network, wherein the overflow and leakage risk early warning model comprises an input layer, a hidden layer and an output layer, and the hidden layer comprises at least two layers of long and short term memory network structures; training an overflow and leakage risk early warning model by using the existing drilling risk data; and (4) performing drilling and leakage early warning on the oil and gas well by using the trained leakage risk early warning model.
According to an exemplary embodiment of the present invention, the long-short term memory network structure of the output layer and the hidden layer can be connected by using a softmax activation function.
According to an exemplary embodiment of the invention, the output layer is capable of outputting a probability of occurrence of at least one of a flooding risk, a lost circulation risk and a normal operating condition.
According to an exemplary embodiment of the present invention, the step of training the early warning model of overflow risk includes: forward propagation of data and backward propagation of errors.
According to an exemplary embodiment of the present invention, the step of training the early warning model of overflow risk includes: step A: setting training parameters of the constructed overflow and leakage risk early warning model; and B: initializing the weight and bias of the constructed overflow and leakage risk early warning model; and C: inputting the drilling risk data, and outputting the actual working condition by the overflow and leakage risk early warning model under the current weight and bias; step D: comparing the actual working condition with the expected output, and reversely propagating layer by layer under the condition that the actual working condition does not meet the expected output, and distributing the error to each layer of the overflow and leakage risk early warning model; step E: and C, adjusting the weight and the bias, and repeating the steps B to D until the output actual working condition meets the expected output.
According to an exemplary embodiment of the present invention, the step of training the early warning model of overflow risk includes: screening drilling risk data from the drilling data, the drilling risk data comprising: the volume of a mud pit on the ground, the pressure of a riser, the outlet flow of drilling fluid at a wellhead, the annular pressure at the bottom of a well and the annular temperature at the bottom of the well; carrying out normalization processing on the drilling risk data, and removing outlier points in the data obtained after the normalization processing; expanding the drilling risk data in an overlapped sampling mode; then, the above steps A to E are carried out.
According to an exemplary embodiment of the present invention, the steps of screening drilling risk data, normalizing, removing outliers, and expanding data may be implemented by an input layer of the overflow risk early warning model.
According to an exemplary embodiment of the invention, the drilling risk data may comprise: the volume of a mud pit on the ground, the pressure of a riser, the outlet flow rate of drilling fluid at a wellhead, the annular pressure at the bottom of a well and the annular temperature at the bottom of the well.
According to an exemplary embodiment of the present invention, before the training of the early warning model of risk of overflow, the method may further include the steps of: and carrying out normalization processing on the drilling risk data.
According to an exemplary embodiment of the present invention, the drilling risk data may be normalized using a maximum method.
According to an exemplary embodiment of the present invention, the method may further comprise the steps of: and removing outlier points in the data obtained after the normalization processing.
According to an exemplary embodiment of the present invention, the well risk data may be augmented in an overlapping sampling manner before the training of the spill risk early warning model.
Compared with the prior art, the beneficial effects of the invention can comprise at least one of the following:
(1) when the overflow and leakage risk monitoring is carried out, the identification result can be timely and accurately given.
(2) The method can avoid the characteristic extraction process of the current mainstream overflow and leakage early warning method, and reduces the dependence of risk identification on prior knowledge and expert experience, so that the early warning of the drilling risk is more intelligent and efficient.
(3) The input and output data of the invention are established according to the artificial intelligence model which does not depend on the theoretical mechanism model seriously, and the requirement on expert experience can be reduced.
(4) With the promotion of digital oil field construction and the establishment of a drilling risk database, the drilling risk early warning method has good field application prospect.
Drawings
The above and other objects and features of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a long short term memory network-based early warning model of risk of overflow of the present invention;
FIG. 2 shows a schematic diagram of the present invention for performing an overlap acquisition;
fig. 3 shows a training flow chart of the early warning model of overflow risk of the present invention.
Detailed Description
Hereinafter, the oil and gas well drilling overflow early warning method based on the long-short term memory network will be described in detail with reference to the accompanying drawings and exemplary embodiments.
The current overflow leakage monitoring method adopted in the drilling site mainly takes manual post-setting monitoring of the liquid level of a mud tank, and is influenced by the sensitivity of a liquid level sensor and the fluctuation of the liquid level of the mud tank, so that the monitoring accuracy is not high. Aiming at the problems of limited real-time performance and accuracy and low intelligent degree of the existing overflow, well leakage and other drilling risk monitoring, the invention combines the characteristics that three monitoring parameters of underground, well head and ground and a Long short-term memory network (LSTM) are suitable for processing strongly coupled and strongly time-dependent data, and provides an intelligent overflow risk early warning method based on the LSTM network, which is used for improving the accuracy of overflow monitoring and early warning.
In an exemplary embodiment of the invention, the oil and gas well drilling overflow early warning method based on the long-short term memory network can comprise the following steps:
s10: an overflow and leakage risk early warning model based on a long-short term memory network is constructed and comprises an input layer, a hidden layer and an output layer, wherein the overflow and leakage risk early warning model is shown in figure 1.
S20: and training the overflow and leakage risk early warning model by using the existing drilling risk data.
S30: and (4) performing drilling and leakage early warning on the oil and gas well by using the trained leakage risk early warning model.
In this embodiment, the input layer may have functions of monitoring parameter selection and data preprocessing.
(1) Monitoring parameter selection
In order to accurately monitor the risk of overflow and lost circulation, appropriate monitoring parameters need to be selected. The invention combines the change characteristics of relevant parameters when the overflow and leakage risk occurs, and can preferably select five parameters of the volume of a mud pit on the ground, the pressure of a stand pipe, the outlet flow of drilling fluid at a wellhead, the annular pressure at the bottom of a well and the annular temperature as parameters for monitoring the overflow and leakage risk.
(2) Data pre-processing
In the actual drilling process, the types of sensors are numerous, the dimensions and the magnitude of different sensors are different, and in order to accelerate the training speed of the network, improve the classification precision and enhance the applicability of the model, before the training of the network model, a data sequence acquired by the sensors is normalized by adopting a most value method, as shown in formula (1).
Wherein the content of the first and second substances,is the value after normalization, xiIs a current value, xminAnd xmaxRespectively representing the minimum and maximum values of the acquired data sequence.
Meanwhile, the influence of noise and random interference on the data acquired on site in the acquisition and transmission processes inevitably causes outliers, and the accuracy of the identification model is influenced. Is provided withIs the mean, σ, of n sampled data sequences2When the nth sample point satisfies the varianceAnd in time, the point is considered as a outlier point, and the outlier point is replaced by the neighborhood mean value.
In addition, the missing data possibly existing in the monitoring data is supplemented by adopting a nearest neighbor interpolation mode.
(3) Data expansion
Further, the input layer may have a function of data expansion. In consideration of relatively less risk data such as overflow, well leakage and the like, in order to avoid network overfitting, the invention provides that a data set is expanded by adopting an overlapped sampling mode. A schematic diagram of overlapping samples is shown in fig. 2. When the model is trained, the data expansion function (namely the link) can be adopted to expand the sample data, and when the model is applied to overflow monitoring, the data expansion function is not needed.
In this embodiment, the hidden layer may be formed by two layers of LSTM structures, and the number, output form, and parameters of neuron nodes included in each layer may be as shown in table 1.
TABLE 1 hidden layer information
Layer | unit | Output Shape | Param |
LSTM1 | 32 | (None,5,32) | 6784 |
LSTM2 | 16 | (None,16) | 3136 |
Wherein None indicates that the dimension cannot be determined, and is related to the number of samples of batch data during neural network training.
In this embodiment, the output layer may be pre-warned for both overflow and lost circulation risks. Each drilling risk may be associated with a type of label, which may be represented by "one-hot vector", for example, in a specific form shown in table 2.
TABLE 2 Risk types and methods of representation
And the output layer and the LSTM unit of the hidden layer can be connected by adopting a softmax activation function, and finally, the overflow risk, the well leakage risk and the probability of the occurrence of normal working conditions are respectively output.
In this embodiment, in step S20, that is, during the training process, 32 groups of data may be randomly extracted from the training samples to form a Batch (Batch), one Batch of data is trained for each iteration, and the training loss value and the test accuracy are recorded. Considering that the number of samples in this experiment is relatively small, in order to prevent the neural network from being overfit, L can be introduced in two LSTM layers2The regularization strategy constrains.
The specific training process includes two parts, namely forward propagation of data and backward propagation of errors, as shown in fig. 3. Firstly, setting training parameters of a network, initializing weight and bias of the network, inputting monitoring data, calculating actual output under the current weight and bias sequentially through an LSTM layer and a full connection layer, calculating error between the actual output and expected output, reversely propagating layer by layer, distributing the error to each layer, and adjusting the weight and the bias of the network by using an Adam algorithm until training conditions are met so as to realize supervised training of the network.
The technical scheme of the invention introduces an advanced deep learning method into the field of drilling risk monitoring of oil and gas wells, and provides a drilling overflow and leakage risk early warning method based on an LSTM network, namely, the LSTM network learns the existing drilling risk data to obtain an overflow and leakage risk early warning model, the acquired original drilling data is preprocessed and then directly input into the trained LSTM network model for overflow and leakage risk monitoring, and the identification result can be timely and accurately given.
Although the present invention has been described above in connection with exemplary embodiments, it will be apparent to those skilled in the art that various modifications and changes may be made to the exemplary embodiments of the present invention without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. An oil and gas well drilling overflow and leakage early warning method based on a long-term and short-term memory network is characterized by comprising the following steps:
constructing an overflow and leakage risk early warning model based on a long and short term memory network, wherein the overflow and leakage risk early warning model comprises an input layer, a hidden layer and an output layer, and the hidden layer comprises at least two layers of long and short term memory network structures;
training an overflow and leakage risk early warning model by using the existing drilling risk data;
and (4) performing drilling and leakage early warning on the oil and gas well by using the trained leakage risk early warning model.
2. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network is characterized in that the output layer is connected with the long-short term memory network structure of the hidden layer by adopting a softmax activation function.
3. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network as claimed in claim 1, wherein the output layer can output the probability of at least one of overflow risk, well leakage risk and normal working condition.
4. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network according to claim 1, wherein the step of training the overflow and leakage risk early warning model comprises the following steps: forward propagation of data and backward propagation of errors.
5. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network as claimed in claim 1, wherein the step of training the overflow and leakage risk early warning model comprises:
step A: setting training parameters of the constructed overflow and leakage risk early warning model;
and B: initializing the weight and bias of the constructed overflow and leakage risk early warning model;
and C: inputting the drilling risk data, and outputting the actual working condition by the overflow and leakage risk early warning model under the current weight and bias;
step D: comparing the actual working condition with the expected output, and reversely propagating layer by layer under the condition that the actual working condition does not meet the expected output, and distributing the error to each layer of the overflow and leakage risk early warning model;
step E: and C, adjusting the weight and the bias, and repeating the steps B to D until the output actual working condition meets the expected output.
6. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network as claimed in claim 1, wherein the drilling risk data comprises:
the volume of a mud pit on the ground, the pressure of a riser, the outlet flow rate of drilling fluid at a wellhead, the annular pressure at the bottom of a well and the annular temperature at the bottom of the well.
7. The oil and gas well drilling spillage early warning method based on the long and short term memory network as claimed in claim 1, wherein before the training of the spillage risk early warning model, the method further comprises the steps of: and carrying out normalization processing on the drilling risk data.
8. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network as claimed in claim 7, wherein the drilling risk data is normalized by adopting a most value method.
9. The method for warning of oil and gas well drilling spillage and leakage of long and short term memory network according to claim 7, wherein the method further comprises the steps of: and removing outlier points in the data obtained after the normalization processing.
10. The oil and gas well drilling overflow and leakage early warning method based on the long-short term memory network as claimed in claim 1, wherein the drilling risk data is expanded in an overlapping sampling mode before the overflow and leakage risk early warning model is trained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010979086.2A CN112016766A (en) | 2020-09-17 | 2020-09-17 | Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010979086.2A CN112016766A (en) | 2020-09-17 | 2020-09-17 | Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112016766A true CN112016766A (en) | 2020-12-01 |
Family
ID=73521436
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010979086.2A Pending CN112016766A (en) | 2020-09-17 | 2020-09-17 | Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112016766A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926839A (en) * | 2021-02-05 | 2021-06-08 | 中国石油大学(华东) | Overflow risk cooperative monitoring method and system for oil and gas well drilling process |
CN113486595A (en) * | 2021-07-23 | 2021-10-08 | 中海石油(中国)有限公司 | Intelligent blowout early warning method, system, equipment and storage medium |
CN115130934A (en) * | 2022-09-01 | 2022-09-30 | 中国石油大学(华东) | Regional lost circulation risk pre-evaluation method based on ZEL model and multi-source data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599520A (en) * | 2016-12-31 | 2017-04-26 | 中国科学技术大学 | LSTM-RNN model-based air pollutant concentration forecast method |
CN109448445A (en) * | 2018-09-05 | 2019-03-08 | 南京航空航天大学 | Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method |
CN110443488A (en) * | 2019-07-31 | 2019-11-12 | 中国石油大学(华东) | The recognition methods of drilling well spill hazard, system and equipment based on convolutional neural networks |
CN110533163A (en) * | 2019-08-02 | 2019-12-03 | 中国石油集团长城钻探工程有限公司 | Sand plugging after fracturing method for early warning based on long Memory Neural Networks in short-term |
CN111175852A (en) * | 2019-12-27 | 2020-05-19 | 中国电子科技集团公司第十四研究所 | Airport fog forecast early warning method based on long-time memory algorithm |
CN111325947A (en) * | 2020-03-04 | 2020-06-23 | 合肥泽众城市智能科技有限公司 | Storm surge flood early warning method and system based on long-term and short-term memory network |
-
2020
- 2020-09-17 CN CN202010979086.2A patent/CN112016766A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106599520A (en) * | 2016-12-31 | 2017-04-26 | 中国科学技术大学 | LSTM-RNN model-based air pollutant concentration forecast method |
CN109448445A (en) * | 2018-09-05 | 2019-03-08 | 南京航空航天大学 | Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method |
CN110443488A (en) * | 2019-07-31 | 2019-11-12 | 中国石油大学(华东) | The recognition methods of drilling well spill hazard, system and equipment based on convolutional neural networks |
CN110533163A (en) * | 2019-08-02 | 2019-12-03 | 中国石油集团长城钻探工程有限公司 | Sand plugging after fracturing method for early warning based on long Memory Neural Networks in short-term |
CN111175852A (en) * | 2019-12-27 | 2020-05-19 | 中国电子科技集团公司第十四研究所 | Airport fog forecast early warning method based on long-time memory algorithm |
CN111325947A (en) * | 2020-03-04 | 2020-06-23 | 合肥泽众城市智能科技有限公司 | Storm surge flood early warning method and system based on long-term and short-term memory network |
Non-Patent Citations (1)
Title |
---|
彭阳;余芳强;许?琳;: "基于长短期记忆网络的空调机组故障诊断与风险评估", 计算机应用, no. 1 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112926839A (en) * | 2021-02-05 | 2021-06-08 | 中国石油大学(华东) | Overflow risk cooperative monitoring method and system for oil and gas well drilling process |
CN113486595A (en) * | 2021-07-23 | 2021-10-08 | 中海石油(中国)有限公司 | Intelligent blowout early warning method, system, equipment and storage medium |
CN113486595B (en) * | 2021-07-23 | 2024-05-14 | 中海石油(中国)有限公司 | Well blowout intelligent early warning method, system, equipment and storage medium |
CN115130934A (en) * | 2022-09-01 | 2022-09-30 | 中国石油大学(华东) | Regional lost circulation risk pre-evaluation method based on ZEL model and multi-source data |
CN115130934B (en) * | 2022-09-01 | 2022-11-04 | 中国石油大学(华东) | Regional well leakage risk pre-evaluation method based on ZEL model and multi-source data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112016766A (en) | Oil and gas well drilling overflow and leakage early warning method based on long-term and short-term memory network | |
CN108388921B (en) | Overflow loss real-time identification method based on random forest | |
EP1984860B1 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
US9934338B2 (en) | Methods and related systems of building models and predicting operational outcomes of a drilling operation | |
Khamehchi et al. | A novel approach to sand production prediction using artificial intelligence | |
US8504341B2 (en) | Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
US9280517B2 (en) | System and method for failure detection for artificial lift systems | |
US20070179766A1 (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator | |
Aljubran et al. | Deep learning and time-series analysis for the early detection of lost circulation incidents during drilling operations | |
Cao et al. | A review on application of data-driven models in hydrocarbon production forecast | |
US20160179751A1 (en) | Viariable structure regression | |
Xue et al. | An automated data-driven pressure transient analysis of water-drive gas reservoir through the coupled machine learning and ensemble Kalman filter method | |
Shadizadeh et al. | Drilling stuck pipe prediction in iranian oil fields: An artificial neural network approach | |
Cao et al. | Field data analysis and risk assessment of shallow gas hazards based on neural networks during industrial deep-water drilling | |
CN107153881B (en) | Drilling risk prediction method | |
Cao et al. | Feature investigation on the ROP machine learning model using realtime drilling data | |
Morooka et al. | Development of intelligent systems for well drilling and petroleum production | |
CN115099406A (en) | Stratum pressure inversion method and device based on multivariate time sequence | |
US20230316152A1 (en) | Method to predict aggregate caliper logs using logging-while-drilling data | |
Nezhad et al. | Stuck drill pipe prediction with networks neural in maroon field | |
Mohamed et al. | Advanced Machine Learning Methods for Prediction of Fracture Closure Pressure, Closure Time, Permeability and Time to Late Flow Regimes From DFIT | |
CN112418489A (en) | Neural network prediction method for dosage of temporary plugging agent for repairing natural gas well | |
CN117933103B (en) | Carbon sequestration model uncertainty analysis method based on Bayesian deep learning | |
CN116006168A (en) | Injection and production parameter optimization method and system based on connectivity analysis | |
Yuan et al. | Quantitative Prediction of Lost Circulation Risk Ahead of Bit Using Leaky Noisy-Or Gate Bayesian Networks and Seismic Attributes |
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 |