CN109138969B - Prediction method and device for drilling state variable and storage device - Google Patents
Prediction method and device for drilling state variable and storage device Download PDFInfo
- Publication number
- CN109138969B CN109138969B CN201810785854.3A CN201810785854A CN109138969B CN 109138969 B CN109138969 B CN 109138969B CN 201810785854 A CN201810785854 A CN 201810785854A CN 109138969 B CN109138969 B CN 109138969B
- Authority
- CN
- China
- Prior art keywords
- state variable
- drilling state
- data
- drilling
- prediction
- 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.)
- Active
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012549 training Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 239000012530 fluid Substances 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 229910052500 inorganic mineral Inorganic materials 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 239000011707 mineral Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Images
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
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
-
- E21B41/0092—
Landscapes
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Physics & Mathematics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Earth Drilling (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a prediction method, a device and a storage device of a drilling state variable. And finally, establishing a drilling state variable prediction model based on support vector regression according to the determined operation parameters and the drilling state parameters. A drilling state variable prediction device and a storage device are used for realizing a drilling state variable prediction method. The invention has the beneficial effects that: the method can realize effective prediction of the drilling state variable and provide good guidance for drilling operation.
Description
Technical Field
The invention relates to the field of geological exploration, in particular to a prediction method, a prediction device and a prediction storage device of a drilling state variable.
Background
The main mineral resources and energy resources in China depend on import from abroad in large quantity, the national security and economic development is restricted by people, and the national resource and energy security must be ensured at home. And the mineral resources in China are rich in energy reserves, and the relative shortage of domestic supply can be relieved by comprehensively exploiting the mineral resources.
However, in the process of developing geological exploration and development, due to the fact that stratum layers encountered by deep drilling are many, a pressure system is complex, rock types are complex and changeable, and the complex stratum mechanical environment with high ground stress, high ground temperature, high osmotic pressure and mining disturbance exists, the problems that equipment cannot be normally used, information transmission is difficult, interference in the drilling process is strong, coupling among systems is serious and the like occur to commonly-used sensor equipment in the drilling process. These problems have resulted in the entire drilling system being a black box system, and the operator can only determine the current drilling status based on experience to a large extent. However, due to different personal experiences, the determination of the current drilling state may be different, which often results in distinct control effects on the drilling process. According to the experience, the judgment and the control of the drilling state have strong personal subjectivity. Therefore, there is a need to develop a method for predicting a drilling state, which is significant for the determination and control of the drilling state.
Disclosure of Invention
In order to solve the problems, the invention provides a prediction method, a prediction device and a storage device of a drilling state variable, wherein the prediction method of the drilling state variable mainly comprises the following steps:
s101: determining operation parameters related to drilling state variables according to a drilling mechanism to obtain data of the operation parameters;
s102: performing low-pass filtering on the data by using a fast Fourier transform method to filter disturbance existing in the data;
s103: establishing a prediction model of the drilling state variable by adopting a support vector regression algorithm according to the filtered data and the drilling state variable corresponding to the operating parameter;
s104: updating the model by using a model updating method to obtain a final prediction model of the drilling state variable;
s105: and inputting the current operating parameter data and the drilling state variable data into a final drilling state variable prediction model, predicting the drilling state variable at the next moment, and obtaining the drilling state at the next moment.
Further, in step S101, the operation parameters include: weight on bit, rotational speed, pump rate and drilling fluid density.
Further, in step S102, the process of filtering data by using the fast fourier filtering method includes:
(1) measurement parameter F of preset cut-off frequencycAccording to equation (1) and a cutoff frequencycSolving for the cut-off frequency fc:
Wherein f iscDenotes the cut-off frequency, FsRepresenting the sampling frequency, FcA metric parameter that is a cut-off frequency;
(2) according to the cut-off frequency fcFiltering out the frequencies greater than a cut-off frequency f present in said datacHigh frequency disturbances of (2), retention requirementsThe signal frequency of (c).
Further, in step S103, the prediction model of the drilling state variable is obtained by taking the drilling operation parameter data and the drilling state variable data at the current moment as model inputs and taking the drilling state variable data at the next moment as model outputs for training; the drilling state variables include current rate of penetration and total pit volume.
A storage device stores instructions and data for implementing a method of predicting a drilling state variable.
A prediction device for a drilling state variable, comprising: a processor and the storage device; the processor loads and executes the instructions and data in the storage device for implementing a drilling state variable prediction method.
The technical scheme provided by the invention has the beneficial effects that: the method can realize effective prediction of the drilling state variable and provide good guidance for drilling operation.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method of predicting a drilling state variable in an embodiment of the present invention;
FIG. 2 is a block diagram of a drilling state variable prediction method in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a model update method in an embodiment of the invention;
fig. 4 is a schematic diagram of the operation of the hardware device in the embodiment of the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
The embodiment of the invention provides a prediction method, a prediction device and a storage device of a drilling state variable.
Referring to fig. 1, fig. 1 is a flowchart of a drilling state variable prediction method according to an embodiment of the present invention, which specifically includes the following steps:
s101: determining operation parameters related to drilling state variables according to a drilling mechanism to obtain data of the operation parameters; in the drilling process, the drilling speed and the total pool volume of a mud pool are important indexes for measuring the drilling efficiency and the safety; the adjustment of the drilling speed is determined by two operation quantities of the drilling pressure and the rotating speed, and the total pool volume of the mud pool is determined by the pump volume and the mud density; in order to realize accurate prediction of the drilling rate and the total pool volume of the mud pool, the operation parameters related to the drilling state variable are obtained, and the operation parameters comprise: bit pressure, rotational speed, pump rate and drilling fluid density;
s102: performing low-pass filtering on the data by using a fast Fourier transform method to filter disturbance existing in the data; the process of using the fast Fourier filtering method to filter data comprises the following steps:
(1) measurement parameter F of preset cut-off frequencycAccording to equation (1) and a cutoff frequencycSolving for the cut-off frequency fc:
Wherein f iscDenotes the cut-off frequency, FsRepresenting the sampling frequency, FcIs a metric parameter of the cut-off frequency.
(2) According to the cut-off frequency fcFiltering out the frequencies greater than a cut-off frequency f present in said datacThe desired signal frequency is preserved.
S103: establishing a prediction model of the drilling state variable by adopting a support vector regression algorithm according to the filtered data and the drilling state variable data corresponding to the operating parameters; the prediction model of the drilling state variable is obtained by taking the drilling operation parameter data and the drilling state variable data at the current moment as model inputs and taking the drilling state variable data at the next moment as model outputs for training; the drilling state variables comprise the current drilling rate and the total pool volume;
s104: updating the model on line by using a model updating method to obtain a final drilling state variable prediction model; the process of updating the model by using the model updating method comprises the following steps: dividing the filtered data and the drilling state variable corresponding to the operating parameter into a test set and a training set, wherein the training set and the test set are respectively provided with n groups of data and k groups of data, and each group of data comprises the drilling operating parameter data at the current moment, the drilling state variable data and the actual drilling state variable data at the next moment; when the prediction model predicts a group of data of the test set, recording the obtained prediction result, and transferring the group of data into a training set; updating the prediction model according to all data in the training set, and using the updated prediction model for processing the next group of data in the test set; the final training set comprises n + k-1 group data; continuously updating the prediction model by continuously transferring the data of the test set to the training set to ensure that the training set continuously contains new data information, so as to obtain the final prediction model of the drilling state variable; so as to obtain a prediction result with higher precision; therefore, the model is continuously updated, and the prediction precision of the model is improved;
s105: and inputting the current operating parameter data and the drilling state variable data into a final drilling state variable prediction model, predicting the drilling state variable data at the next moment, and obtaining the drilling state at the next moment.
Referring to fig. 2, fig. 2 is a structural diagram of a drilling state variable prediction method according to an embodiment of the present invention, and the concrete steps of prediction by using a model are as follows:
(1) obtaining operating parameter data
Collecting data obtained in real time in 2805-2833 m well sections of a drilling field, removing data of drill stopping and drill tripping in the data, selecting 1100 groups of data, selecting drilling speed and total pool volume of a mud pool as state variables, and selecting drilling pressure, rotating speed, pump capacity and drilling fluid density as operating parameters.
(2) Data filtering based on fast Fourier transform
Some high-frequency disturbance exists in the obtained data, so that the data is filtered by using a fast Fourier change method to filter the high-frequency disturbance existing in the data.
(3) Establishing a drilling state variable prediction model
The amplitudes of different variables are different, the difference of the amplitudes causes great difference among sample data, and in order to eliminate the influence of the amplitudes, normalization processing is carried out on each sample data.
And taking the current operating parameters and the drilling state variables as the input of a prediction model, and taking the drilling state variables at the next moment as the output of the model. 1080 sets were selected from 1100 samples to train the model, and the remaining 20 sets were used to test the model performance. And constructing a model by using a Support Vector Regression (SVR) method, and then continuously updating the model by using a model updating method.
Referring to fig. 3, fig. 3 is a schematic diagram of a model updating method according to an embodiment of the present invention, first dividing data into a test set and a training set according to a time sequence, assuming that the test set and the training set respectively have n groups of data and k groups of data; then, when the model predicts a group of data in the test set, the data is transferred to a training set, the model is updated according to the data in the training set, and the obtained prediction result is recorded; continuously transferring the data of the prediction set to a training set, wherein the final training set comprises n + k-1 group data; the training set continuously contains new data information to realize continuous updating of the model and obtain a prediction result with higher precision; therefore, the model is continuously updated, and the prediction precision of the model is improved.
Measuring the prediction performance of the model by adopting a mean square error method, and obtaining the mean square error between the true value and the predicted value according to a formula (3):
where MSE is the mean square error, yiThe actual value is represented by the value of,representing a predicted value; the smaller the MSE, the more the model is representedThe better the measurement performance, the closer the predicted value is to the true value, and the higher the prediction precision of the model is.
In the embodiment of the invention, the MSEs of the drilling rate and the total pool volume are obtained by prediction and are 0.000465 and 0.00110 respectively, which shows that the technical scheme provided by the invention has higher prediction precision.
Referring to fig. 4, fig. 4 is a schematic diagram of a hardware device according to an embodiment of the present invention, where the hardware device specifically includes: a drilling state variable prediction device 401, a processor 402 and a storage device 403.
A prediction device 401 of drilling state variables: the prediction device 401 of the one drilling state variable implements the prediction method of the one drilling state variable.
The processor 402: the processor 402 loads and executes instructions and data in the memory device 403 for implementing the one drilling state variable prediction method.
The storage device 403: the storage device 403 stores instructions and data; the memory device 403 is used to implement the one drilling state variable prediction method.
The invention has the beneficial effects that: the method can realize effective prediction of the drilling state variable and provide good guidance for drilling operation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (5)
1. A method of predicting a drilling state variable, comprising: the method comprises the following steps:
s101: determining operation parameters related to drilling state variables according to a drilling mechanism to obtain data of the operation parameters;
s102: performing low-pass filtering on the data by using a fast Fourier transform method to filter disturbance existing in the data;
s103: establishing a prediction model of the drilling state variable by adopting a support vector regression algorithm according to the filtered data and the drilling state variable data corresponding to the operating parameters;
s104: updating the model by using a model updating method, measuring the prediction performance of the model by using a mean square error method in the updating process, and obtaining the mean square error between the true value and the predicted value according to a formula (3):
where MSE is the mean square error, yiThe actual value is represented by the value of,representing a predicted value; the smaller the MSE is, the better the prediction performance of the model is, the closer the predicted value is to the true value, and the higher the prediction precision of the model is;
after continuously updating for a plurality of times, the prediction precision is kept unchanged, and a final prediction model of the drilling state variable is obtained;
s105: and inputting the current operating parameter data and the drilling state variable data into a final drilling state variable prediction model, predicting the drilling state variable data at the next moment, and obtaining the drilling state at the next moment.
2. A method of predicting a drilling state variable as claimed in claim 1, wherein: in step S101, the operation parameters include: weight on bit, rotational speed, pump rate and drilling fluid density.
3. A method of predicting a drilling state variable as claimed in claim 1, wherein: in step S103, the drilling state variable prediction model is obtained by taking the drilling operation parameter data and the drilling state variable data at the current moment as model inputs and taking the drilling state variable data at the next moment as model outputs for training; the drilling state variables include current rate of penetration and total pit volume.
4. A storage device, characterized by: the storage device stores instructions and data for implementing a method of predicting a drilling state variable as claimed in any one of claims 1 to 3.
5. A prediction apparatus of a drilling state variable, characterized by: the method comprises the following steps: a processor and the storage device of claim 4; the processor loads and executes the instructions and data in the storage device to realize the prediction method of the drilling state variable according to any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810785854.3A CN109138969B (en) | 2018-07-17 | 2018-07-17 | Prediction method and device for drilling state variable and storage device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810785854.3A CN109138969B (en) | 2018-07-17 | 2018-07-17 | Prediction method and device for drilling state variable and storage device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109138969A CN109138969A (en) | 2019-01-04 |
CN109138969B true CN109138969B (en) | 2021-07-13 |
Family
ID=64800862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810785854.3A Active CN109138969B (en) | 2018-07-17 | 2018-07-17 | Prediction method and device for drilling state variable and storage device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109138969B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117287179B (en) * | 2023-11-27 | 2024-02-06 | 张家港市胜港机械制造有限公司 | Remote control system and method for precision drilling and production equipment |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103581188B (en) * | 2013-11-05 | 2016-08-03 | 中国科学院计算技术研究所 | A kind of network security situation prediction method and system |
CN106372731B (en) * | 2016-11-14 | 2017-07-28 | 中南大学 | A kind of high wind line of high-speed railway wind speed spatial network structure forecast method |
CN106909759B (en) * | 2017-04-11 | 2019-08-06 | 中国石油大学(北京) | A kind of shale formation PDC drill bit rate of penetration prediction technique and device |
CN108134691B (en) * | 2017-12-18 | 2019-10-01 | Oppo广东移动通信有限公司 | Model building method, Internet resources preload method, apparatus, medium and terminal |
CN108133289A (en) * | 2017-12-21 | 2018-06-08 | 中国铁建电气化局集团有限公司 | Tunnel ventilation control method and system based on environmental forecasting |
CN108189036B (en) * | 2018-01-17 | 2021-08-13 | 广州视源电子科技股份有限公司 | Torque control method and device, robot and storage medium |
-
2018
- 2018-07-17 CN CN201810785854.3A patent/CN109138969B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109138969A (en) | 2019-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111441758B (en) | Shale oil gas dessert area prediction method and device | |
Ahmadi et al. | Connectionist model predicts the porosity and permeability of petroleum reservoirs by means of petro-physical logs: application of artificial intelligence | |
Ahmadi | Connectionist approach estimates gas–oil relative permeability in petroleum reservoirs: application to reservoir simulation | |
CN105874159A (en) | Controlling wellbore drilling systems | |
BR112015009197B1 (en) | METHOD AND SYSTEM FOR PERFORMING A DRILLING OPERATION | |
US10620339B2 (en) | Static earth model calibration methods and systems using tortuosity evaluations | |
US10145985B2 (en) | Static earth model calibration methods and systems using permeability testing | |
GB2463420A (en) | Method programme and commputer system for scaling the modelling data for a hydrocarbon deposit | |
KR102294384B1 (en) | Method for constructing drilling driving guide model to predict drilling rate using machine learning and system for predicting drilling rate using thereof | |
CN105849363A (en) | Controlling a bottom hole assembly in a wellbore | |
JP7137889B2 (en) | Prediction method of the lower limit of oil pool endowment depth of carbonatite in the deep-ultra-deep ocean facies | |
Zhang et al. | Estimation of fracture stiffness, in situ stresses, and elastic parameters of naturally fractured geothermal reservoirs | |
CN109138969B (en) | Prediction method and device for drilling state variable and storage device | |
Qin et al. | Predicting pore-water pressure in front of a TBM using a deep learning approach | |
CN114002129B (en) | High-water-pressure-crack rock mass seepage test platform | |
Zhdaneev et al. | Predictive systems for the well drilling operations | |
CA2874978C (en) | Methods and systems for non-physical attribute management in reservoir simulation | |
CN111997581B (en) | Heterogeneous oil reservoir development method and device and electronic equipment | |
Ma et al. | Directional fast drilling technology in Yanchang gas field with quartz sandstone geology | |
US11867048B2 (en) | Method and system based on quantified flowback for formation damage removal | |
Chen et al. | GINI coefficient: An effective way to evaluate inflow profile equilibrium of horizontal wells in Shengli Oil Field | |
Zhou et al. | Prediction of ROP and MPV Based on Support Vector Regression Method | |
Chernyi | The problems of automation technological process of drilling oil and gas wells | |
Xie et al. | Improving Drilling Efficiency Using Intelligent Decision System for Drilling in Bohai Oilfield Based on Big Data | |
Wang et al. | Data Integration Enabling Advanced Machine Learning ROP Predictions and its Applications |
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 |