CN111737868A - Natural gamma curve prediction while drilling method based on time series algorithm - Google Patents
Natural gamma curve prediction while drilling method based on time series algorithm Download PDFInfo
- Publication number
- CN111737868A CN111737868A CN202010549038.XA CN202010549038A CN111737868A CN 111737868 A CN111737868 A CN 111737868A CN 202010549038 A CN202010549038 A CN 202010549038A CN 111737868 A CN111737868 A CN 111737868A
- Authority
- CN
- China
- Prior art keywords
- drilling
- gamma curve
- natural gamma
- time series
- predicting
- 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 52
- 238000000034 method Methods 0.000 title claims abstract description 33
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 27
- 238000012795 verification Methods 0.000 claims abstract description 4
- 238000005311 autocorrelation function Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is applied to the technical field of wireless logging while drilling parameter prediction, and discloses a method for predicting a natural gamma curve while drilling based on a time series algorithm, which comprises the following steps: collecting a natural gamma curve of a drilled well, establishing an ARIMA model of the natural gamma curve while drilling on a time sequence, and then predicting the natural gamma curve at a drill bit. The verification result of the actual drilling data shows that the method predicts that the natural gamma curve accords with the actual condition, can reflect the actual condition of the stratum encountered by the drill bit before measuring the natural gamma curve while drilling, and does not have the problem of measuring zero length.
Description
Technical Field
The invention belongs to the technical field of wireless logging while drilling parameter prediction, and particularly relates to a method for predicting a natural gamma curve while drilling based on a time series algorithm.
Background
In recent years, the distance between the downhole geologic parameter and the drill bit has become critical when the geologic condition is complex or when steering the well in thin pay zones. Because the near-bit measurement while drilling technology has high difficulty and high cost, and has a large gap with foreign technologies, the near-bit LWD cannot be achieved. In the geosteering well drilling, a sensor of an LWD wireless drilling instrument is 8-20m away from a drill bit, data of a measuring point cannot correctly reflect actual formation parameter information of the position of the drill bit, natural gamma parameters within the range of 8-20m away from the drill bit are intelligently measured, formation characteristics at the drill bit cannot be obtained, the actual condition of entering a reservoir cannot be judged, and certain difficulty is brought to judging whether the natural gamma parameters enter the reservoir.
Disclosure of Invention
The invention aims to make up for the defects of the prior art and provides a method for predicting a natural gamma curve while drilling based on a time series algorithm.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for predicting a natural gamma curve while drilling based on a time series algorithm comprises the following steps:
step S1, establishing a data set: collecting while-drilling gamma data of a drilled well, and cleaning the data;
s2, constructing an ARIMA model according to whether the original sequence is stable and different regression parts;
step S3, selecting the optimal ARIMA model: verifying the established ARIMA model and selecting the optimal parameters;
step S4, natural gamma curve prediction while drilling: and predicting the natural gamma curve value at the drill bit according to the optimal ARIMA model.
Further, the data cleansing process in step S1 is as follows: and removing the gamma value and the singular value recorded in a non-drilling mode from the originally recorded gamma value while drilling, and then carrying out measurement well depth averaging to obtain the gamma value while drilling of the drilled well.
Further, the ARIMA model constructed in step S2 is denoted as ARIMA (p, d, q), where p is the number of autoregressive terms, q is the number of moving average terms, and d is the number of differences made when the time series becomes stationary.
Further, after the ARIMA model is constructed in step S2, data stationarity check is performed to detect whether the first-order difference and the second-order difference of the natural gamma curve values while drilling are stationary.
Further, the step S3 specifically includes the following steps:
step S31, calculating an autocorrelation function ACF and a partial autocorrelation function PACF according to the difference result, and selecting proper values of p and q from the ACF and PACF test modes;
step S32, selecting parameters: testing different combinations of p and q, and selecting the optimal model parameters by applying AIC (automatic analytical analysis) criteria;
step S33, model verification: the model is verified to be accurate by checking if the residual is a white noise sequence.
The invention has the beneficial effects that:
(1) compared with the prior art, the method can realize the prediction of the natural gamma curve value at the drill bit;
(2) compared with other methods, the method based on time series analysis does not need a large number of samples for modeling, and solves the difficulty of insufficient samples.
Drawings
FIG. 1 is an algorithm flow of a method for predicting a natural gamma curve while drilling based on a time series algorithm according to the present invention;
FIG. 2 is an ACF value of a natural gamma curve while drilling prediction method based on a time series algorithm according to the present invention;
FIG. 3 is a PACF value of a method for predicting a natural gamma curve while drilling based on a time series algorithm provided by the present invention;
FIG. 4 is a first-order difference value of a natural gamma curve while drilling prediction method based on a time series algorithm according to the present invention;
FIG. 5 is a residual error detection Q-Q diagram related to a natural gamma curve while drilling prediction method based on a time series algorithm provided by the invention;
FIG. 6 is a comparison between a predicted value and a true value of a natural gamma curve while drilling prediction method based on a time series algorithm provided by the invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
a flow chart of a method for predicting a natural gamma curve while drilling based on a time series algorithm is shown in FIG. 1, and the method specifically comprises the following steps:
step S1: establishing a data set: and selecting a natural gamma curve while drilling of the drilled well as a data set.
Further, the gamma value while drilling of the drilled well bore is the gamma value obtained by removing the gamma value and the singular value recorded in a non-drilling mode from the original gamma value while drilling and then averaging the measured well depth.
Step S2: establishing an ARIMA model: the establishing of the ARIMA model comprises a plurality of processes, such as a moving average process MA, an autoregressive process AR, an autoregressive moving average process ARMA and an ARIMA process, and the corresponding processes can be selected according to whether the original sequence is stable and the difference of regression parts so as to establish the ARIMA model; the constructed ARIMA model is marked as ARIMA (p, d, q), wherein p is the number of autoregressive terms, q is the number of moving average terms, and d is the difference times when the time sequence becomes stable.
Further, in step S2, a data stationarity check is performed: and drawing a time sequence diagram, evaluating the diagram, performing first-order difference and second-order difference on the processed natural gamma curve while drilling, and evaluating the stability of the natural gamma curve while drilling.
First order difference calculation formula:
Δxt＝xt-xt-1
wherein, Δ xtIs the first order difference value, x, of the natural gamma curve while drilling at adjacent timestIs a natural gamma curve value, x, while drilling at the time tt-1And the value is the natural gamma curve value while drilling at the time t-1.
Second order difference calculation formula:
wherein,
is the second order difference value of the natural gamma curve while drilling at adjacent time, delta xt-1The first-order difference value of the natural gamma curve while drilling at the time of t-1.
As can be seen from the first-order difference result of the natural gamma curve while drilling shown in FIG. 4, the first-order difference of the natural gamma curve while drilling satisfies the requirement of the stationary sequence; fitting stationary time series ARIMA: using { xtRepresents the stationary time series after differencing and calculates the autoregressive moving average process model parameters.
Autoregressive moving average process model:
wherein, x'tAs an autoregressive moving average process function, utIs white noise, θiIn order to move the mean regression parameters,
as an autoregressive parameter, ut-iFor the ith differential time series at time t, xt-iAnd the difference is an error sequence of the ith difference predicted value sequence and the ith difference real value sequence at the time t.
Step S3: selecting an optimal ARIMA model: and verifying the established ARIMA model and selecting the optimal parameters.
Further, the step S3 specifically includes the following steps:
step S31: an autocorrelation function ACF and a partial autocorrelation function PACF are calculated based on the difference results, and appropriate values of p and q are selected from the ACF and PACF test patterns.
From the ACF values and PACF values shown in fig. 2 and 3, parameters p, 2,3, d, and q of the time series ARIMA model are determined to be 1,2,3, and 4.
Step S32: selecting parameters: different combinations of p and q are tested and the optimal model parameters are selected using the AIC criterion.
The AIC criterion is a standard for judging the quality of a model based on a statistical principle:
AIC＝k-ln(l)
wherein k is the number of model parameters, and l is the model prediction maximum likelihood function.
According to this principle, the AIC value of ARIMA (2, 1, 2) is the smallest as the optimal time series model.
Step S33: and (3) model verification: whether the model is accurate or not is verified by checking whether the residual is a white noise sequence, and as shown in fig. 5, the Q-Q value of the residual is in a linear relation and conforms to normal distribution, which indicates that the model is reasonable.
Step S4: predicting a natural gamma curve while drilling: the natural gamma curve data at the drill bit is predicted according to the optimal ARIMA model, and the prediction results are shown in fig. 6.
In summary, the present invention is not limited to the above-mentioned embodiments, and those skilled in the art can propose other embodiments within the technical teaching of the present invention, but these embodiments are included in the scope of the present invention.
Claims (5)
1. A method for predicting a natural gamma curve while drilling based on a time series algorithm is characterized by comprising the following steps:
step S1, establishing a data set: collecting while-drilling gamma data of a drilled well, and cleaning the data;
s2, constructing an ARIMA model according to whether the original sequence is stable and different regression parts;
step S3, selecting the optimal ARIMA model: verifying the established ARIMA model and selecting the optimal parameters;
step S4, natural gamma curve prediction while drilling: and predicting the natural gamma curve value at the drill bit according to the optimal ARIMA model.
2. The method for predicting a natural gamma curve while drilling based on the time series algorithm as recited in claim 1, wherein the data cleaning in the step S1 comprises the following steps: and removing the gamma value and the singular value recorded in a non-drilling mode from the originally recorded gamma value while drilling, and then carrying out measurement well depth averaging to obtain the gamma value while drilling of the drilled well.
3. The method for predicting a natural gamma curve while drilling based on a time series algorithm as recited in claim 1, wherein the ARIMA model constructed in the step S2 is denoted as ARIMA (p, d, q), where p is the number of autoregressive terms, q is the number of moving average terms, and d is the difference times when the time series becomes stationary.
4. The method for predicting the natural gamma curve while drilling based on the time series algorithm as recited in claim 3, wherein a data stationarity test is required after the ARIMA model is constructed in the step S2, and whether a first-order difference and a second-order difference of the natural gamma curve while drilling values are stable or not is detected.
5. The method for predicting a natural gamma curve while drilling based on a time series algorithm as recited in claim 4, wherein the step S3 specifically comprises the following steps:
step S31, calculating an autocorrelation function ACF and a partial autocorrelation function PACF according to the difference result, and selecting proper values of p and q from the ACF and PACF test modes;
step S32, selecting parameters: testing different combinations of p and q, and selecting the optimal model parameters by applying AIC (automatic analytical analysis) criteria;
step S33, model verification: the model is verified to be accurate by checking if the residual is a white noise sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010549038.XA CN111737868A (en) | 2020-06-16 | 2020-06-16 | Natural gamma curve prediction while drilling method based on time series algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010549038.XA CN111737868A (en) | 2020-06-16 | 2020-06-16 | Natural gamma curve prediction while drilling method based on time series algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111737868A true CN111737868A (en) | 2020-10-02 |
Family
ID=72649421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010549038.XA Pending CN111737868A (en) | 2020-06-16 | 2020-06-16 | Natural gamma curve prediction while drilling method based on time series algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111737868A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149311A (en) * | 2020-10-12 | 2020-12-29 | 北京中恒利华石油技术研究所 | Nonlinear multivariate statistical regression logging curve prediction method based on quantity specification |
| CN117077462A (en) * | 2023-10-18 | 2023-11-17 | 中国科学院地质与地球物理研究所 | Method and system for optimizing gamma logging while drilling curve of deep oil gas accurate navigation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103790579A (en) * | 2014-01-03 | 2014-05-14 | 中国石油天然气股份有限公司 | Method and device for determining distance between drill bit and stratum interface in while-drilling geological steering |
| US20150212974A1 (en) * | 2014-01-24 | 2015-07-30 | International Business Machines Corporation | Fast and automated arima model initialization |
| CN108561119A (en) * | 2017-12-05 | 2018-09-21 | 西南石油大学 | A kind of drilling well overflow safety closed-in time prediction technique and system |
| CN110778307A (en) * | 2019-10-24 | 2020-02-11 | 西南石油大学 | Drill jamming early warning and type diagnosis method |
-
2020
- 2020-06-16 CN CN202010549038.XA patent/CN111737868A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103790579A (en) * | 2014-01-03 | 2014-05-14 | 中国石油天然气股份有限公司 | Method and device for determining distance between drill bit and stratum interface in while-drilling geological steering |
| US20150212974A1 (en) * | 2014-01-24 | 2015-07-30 | International Business Machines Corporation | Fast and automated arima model initialization |
| CN108561119A (en) * | 2017-12-05 | 2018-09-21 | 西南石油大学 | A kind of drilling well overflow safety closed-in time prediction technique and system |
| CN110778307A (en) * | 2019-10-24 | 2020-02-11 | 西南石油大学 | Drill jamming early warning and type diagnosis method |
Non-Patent Citations (2)
| Title |
|---|
| 赵春兰 等: "基于ARIMA 模型的钻井作业风险预测", 《新疆石油地质》 * |
| 郭永恒: "随钻测井曲线预测及更新方法研究", 《石油钻探技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149311A (en) * | 2020-10-12 | 2020-12-29 | 北京中恒利华石油技术研究所 | Nonlinear multivariate statistical regression logging curve prediction method based on quantity specification |
| CN117077462A (en) * | 2023-10-18 | 2023-11-17 | 中国科学院地质与地球物理研究所 | Method and system for optimizing gamma logging while drilling curve of deep oil gas accurate navigation |
| CN117077462B (en) * | 2023-10-18 | 2023-12-12 | 中国科学院地质与地球物理研究所 | Method and system for optimizing gamma logging while drilling curve of deep oil gas accurate navigation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20100076740A1 (en) | System and method for well test design and interpretation | |
| US20060047489A1 (en) | Method of modelling the production of an oil reservoir | |
| US10809416B2 (en) | Inversion-based workflow for processing nuclear density images in high-angle and horizontal wells | |
| CN103486971B (en) | A kind of subway tunnel fracture width detection and correcting algorithm | |
| CN111737868A (en) | Natural gamma curve prediction while drilling method based on time series algorithm | |
| CN114279842B (en) | Method and system for determining cracking stress and damage stress of rock cracks | |
| WO2010019798A2 (en) | Bottom hole assembly configuration management | |
| MX2007014065A (en) | Methods for analysis of pressure response in underground formations. | |
| CN109190272B (en) | Concrete structure defect detection method based on elastic waves and machine learning | |
| KR20130100266A (en) | Method for inspecting the quality of a solder joint | |
| Peterson et al. | The good, the bad and the outliers: automated detection of errors and outliers from groundwater hydrographs | |
| CN110596757B (en) | Method for correcting longitudinal wave and transverse wave velocities of shale formation | |
| CN109543915B (en) | Method for identifying total organic carbon content of hydrocarbon source rock in whole well section based on logging information | |
| US20110166842A1 (en) | Layer stripping method | |
| WO2009102526A2 (en) | Methods for the identification of bubble point pressure | |
| CN111520126A (en) | Density logging hole enlargement correction method and device | |
| CN104516991A (en) | Gamma sensor full-temperature range compensation method | |
| CN114991757A (en) | Formation pressure measurement and recording integrated monitoring method and system while drilling | |
| EP2370672A1 (en) | Method and apparatus for real time oil based mud contamination monitoring | |
| CN110956112B (en) | Novel high-reliability slewing bearing service life assessment method | |
| CN110414085B (en) | Method for determining original oil-water interface of developed fault block oil reservoir | |
| CN116881643A (en) | Sensory data depth signal complement method and device | |
| CN111456726A (en) | Sound wave time difference correction method and device | |
| Lu et al. | Improved estimation and forecasting through residual-based model error quantification | |
| CN104278990B (en) | Log data quality restoration methods and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |