CN110852144A - DTW-based intelligent stratum comparison method and system - Google Patents
DTW-based intelligent stratum comparison method and system Download PDFInfo
- Publication number
- CN110852144A CN110852144A CN201910785222.1A CN201910785222A CN110852144A CN 110852144 A CN110852144 A CN 110852144A CN 201910785222 A CN201910785222 A CN 201910785222A CN 110852144 A CN110852144 A CN 110852144A
- Authority
- CN
- China
- Prior art keywords
- logging
- stratum
- matching cost
- matching
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 61
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 64
- 238000010606 normalization Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005755 formation reaction Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 10
- 238000005457 optimization Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000001186 cumulative effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000003208 petroleum Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013517 stratification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Signal Processing (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides an intelligent stratum comparison method and system based on DTW (delay tolerant W). firstly, original logging data are obtained and normalized preprocessing is carried out to form normalized logging data; then extracting variable point information by adopting a variable point detection algorithm to layer the logging curves, thereby dividing each well into stratum units of different levels according to the stratum sequence; and finally, carrying out stratum comparison and matching: and calculating the form similarity information of the logging curves of the two selected wells based on a dynamic time warping algorithm (DTW), calculating and processing the curve characteristics by at least combining the formation depth, thickness and mean value information through a dynamic waveform matching algorithm to determine a minimum matching path, backtracking the minimum matching path to match the formation units and judging whether the formation is missing or not and outputting. The intelligent comparison of the stratum can be more accurately carried out, and the stratum comparison efficiency is improved.
Description
Technical Field
The invention relates to the technical field of formation data processing, in particular to an intelligent formation comparison method and system based on DTW.
Background
With the gradual deepening of oil field exploration work, exploration objects are more and more complex, and exploration target optimization and exploratory well deployment requirement research work are more and more refined. The oil-gas exploration and development is a process of continuously acquiring, processing and converting underground oil-gas reservoir data into information, wherein the data contains information and the information contains oil-gas resources. How to utilize advanced software and hardware tools to the maximum extent under a unified computing environment enables data reflecting complex geological objects to be comprehensively and efficiently integrated and visually and conveniently displayed in front of researchers in a visual mode, so that geological data can be deeply analyzed and applied, decision support is provided for exploration work, and development needs of the petroleum industry are met.
Stratum contrast is one of basic works for researching stratum structures, structures and deposition environments, is indispensable work in oil and gas exploration and development, currently, manual contrast is mainly used, and development of related computer programs is very deficient. The quality of manual comparison depends on the knowledge structure and experience accumulation of people, so that the interpretation of different people is different in the same block, the repeatability is poor, the multi-solution is strong, when logging geology personnel carry out stratum comparison, the consideration is not only the form of a curve but also various information of the curve, the optimal solution is obtained according to rich knowledge, but the labor intensity of the comparison is high, and the working efficiency is low; the existing computer program comparison is carried out by taking parameters such as depth, thickness, mean value, variance and the like as weights, the comparison effect extremely depends on information such as depth, thickness and the like, lithological characteristics cannot be used when large-cycle comparison is carried out, and geological significance reflected by curve form information is not considered; the method utilizes methods such as machine learning to cluster and classify stratums, does not consider geological laws such as Wolson phase law and sequence stratigraphy, only considers similarity of curve parameters, and lacks interpretability.
Disclosure of Invention
In order to solve the problems that the manual stratum comparison work intensity is high, the efficiency is low, the repeatability is poor, the existing computer program comparison method is lack of interpretability and the like in the prior art, the invention provides an intelligent stratum comparison method based on DTW (dynamic time warping), the DTW algorithm is based, the characteristic parameters such as the form similarity, the depth, the thickness, the mean value and the like of a logging curve are fused to carry out logging curve matching cost, and then the dynamic waveform matching algorithm is used for carrying out stratum comparison to match stratum units, so that the intelligent comparison of the stratum can be carried out more accurately, and the stratum comparison efficiency is improved. The invention also relates to an intelligent stratigraphic comparison system based on the DTW.
The technical scheme of the invention is as follows:
an intelligent formation comparison method based on DTW comprises the following steps:
the first step is as follows: acquiring original logging data and carrying out normalization preprocessing to form normalized logging data;
the second step is as follows: extracting variable point information of the normalized logging data by adopting a variable point detection algorithm based on a sliding window so as to stratify the logging curve of each well to obtain stratigraphic units of different levels;
the third step: extracting the logging curve characteristics of the wells to be compared, wherein the logging curve characteristics at least comprise logging curve form similarity, depth, thickness and mean value information, and the logging curve form similarity information is obtained through a DTW algorithm; and calculating and processing the logging curve characteristics by a dynamic waveform matching algorithm to determine a matching path of the stratum, and backtracking the matching path to match stratum units so as to judge whether the stratum is missing or not and output.
The third step includes the steps of:
s31: extracting the logging curve form similarity of the wells to be compared and at least depth, thickness and mean value information, wherein the logging curve form similarity is obtained through calculation of a DTW algorithm;
s32: sequentially calculating the distance coefficient/local matching cost of each stratigraphic unit of the comparison well to establish a local matching cost matrix;
s33: based on the local matching cost matrix, obtaining a global matching cost matrix through a dynamic waveform matching algorithm, and screening out the minimum global matching cost in the global matching cost matrix;
s34: and backtracking the minimum global matching cost to obtain a shortest path, and matching the stratum units according to a judgment criterion to judge whether a missing stratum exists or not and outputting.
The first step comprises the steps of: for the logging data of different sources, firstly, 95% of the logging data of each source is respectively extracted as the maximum value, 5% of the logging data of each source is extracted as the minimum value, and then the normalized logging data of the logging data of each source is respectively obtained by combining a normalized calculation formula, so that the numerical range of the logging data of each source is distributed between [0,1 ].
The second step includes the steps of: selecting two sliding windows with equal length along the data stream, and comparing each statistical characteristic of the two sliding windows through a variable point detection algorithm to obtain difference measurement; drawing a difference curve according to the relation between the difference measurement and the data stream; and detecting the peak value of the difference curve, repeating the process along the data flow until the variable point detection in all the data flows in each well is completed, and layering the logging curve at each variable point to obtain the stratigraphic units with different levels.
The variable point detection algorithm calculates the difference metric as the difference between the loss function in the two selected sliding windows and the loss function of each sliding window individually, which detects the change in the mean of the signal of the gaussian function projected onto the high-dimensional regenerated hilbert space.
An intelligent stratum contrast system based on DTW comprises a first device, a second device and a third device which are connected in sequence,
the first device is used for acquiring original logging data and carrying out normalization preprocessing to form normalized logging data;
the second device extracts the variable point information of the normalized logging data by adopting a variable point detection algorithm based on a sliding window so as to stratify the logging curve of each well and obtain stratigraphic units of different levels;
the third device extracts the logging curve characteristics of the wells to be compared, wherein the logging curve characteristics at least comprise logging curve form similarity, depth, thickness and mean value information, and the logging curve form similarity information is obtained through a DTW algorithm; and calculating and processing the logging curve characteristics by a dynamic waveform matching algorithm to determine a matching path, and backtracking the matching path to match the stratum units so as to judge whether a missing stratum exists and output.
The first device comprises a data acquisition device and a normalization preprocessing device which are sequentially connected, wherein the data acquisition device receives original logging data and sends the original logging data to the normalization preprocessing device, and the normalization preprocessing device converts the original logging data from different sources into normalization logging data distributed in a [0,1] range.
The second device comprises a variable point detection device and a layering device which are connected in sequence, the variable point detection device comprises a data selection device, a difference characteristic calculation device, a curve generation device and a peak value detection device which are connected in sequence, the data selection device is connected with the normalization preprocessing device, for receiving the normalized logging data and selecting two sliding windows of equal length along the data stream, the difference characteristic calculating device compares each statistical characteristic of the two sliding windows and calculates a difference metric value by a variable point detection algorithm, said curve generating means draws a difference curve from said difference measure along the data stream, said peak detecting means detects the peak of said difference curve, and the layering device is connected with the peak value detection device and is used for layering the logging curves at each variable point to obtain the stratigraphic units with different levels.
The third device comprises a curve form similarity calculation device, a feature extraction device, a matching device, a deletion judgment device and an output device which are connected in sequence, wherein the curve form similarity calculation device is connected with the layering device and calculates the logging curve form similarity between any two stratum units of two logging curves to be compared based on a DTW (delay tolerant shift) algorithm, the feature extraction device extracts the logging curve form similarity and at least depth, stratum thickness and mean value information of each stratum unit of the two logging curves to be compared, the matching device calculates the distance coefficient/local matching cost of each stratum unit of a comparison well in sequence to establish a local matching cost matrix, obtains the global matching cost matrix through a dynamic waveform matching algorithm based on the local matching cost matrix and screens out the minimum global matching cost in the global matching cost matrix, and backtracking the minimum global matching cost to obtain the shortest path, matching the stratum units by the missing judgment device according to a judgment criterion, judging whether a missing stratum exists or not, and outputting a result by the output device.
The matching device comprises a local matching cost matrix generating device, a global matching cost matrix generating device and a shortest path backtracking device which are sequentially connected, wherein the local matching cost matrix generating device sequentially calculates the distance coefficient/local matching cost of each stratum unit of a comparison well to establish a local matching cost matrix, the global matching cost matrix generating device acquires the global matching cost matrix through a dynamic waveform matching algorithm based on the local matching cost matrix, the minimum global matching cost is screened out from the global matching cost matrix, and the shortest matching path of the minimum global matching cost is backtracked by the shortest path backtracking device to match the stratum units so as to judge whether missing strata exist.
The invention has the beneficial technical effects that:
the invention relates to an intelligent stratum comparison method based on DTW, which comprises the steps of firstly, obtaining original logging data and carrying out normalization pretreatment to form normalized logging data, so that the numerical range of the logging data of each source is distributed between [0,1 ]; then extracting variable point information of the normalized logging data of each well by adopting a variable point detection algorithm to layer the logging curve, thereby dividing each well into stratum units of different levels according to the stratum sequence; and finally, carrying out stratum comparison and matching: and calculating the form similarity information of the logging curves of the two selected wells based on a dynamic time warping algorithm (DTW), calculating and processing the curve characteristics by at least combining the formation depth, thickness and mean value information through a dynamic waveform matching algorithm to determine a minimum matching path, backtracking the minimum matching path to match the formation units and judging whether the formation is missing or not and outputting. The method of the invention obtains the similarity information of the logging curve form by a dynamic time warping algorithm for each stratigraphic unit after layering, excavates the geological rule contained in the logging curve form, simultaneously calculates the local matching cost between each stratigraphic unit among wells to be compared by combining parameters such as depth, thickness, lithology and the like, establishes a local matching cost matrix, preferentially obtains a global matching cost matrix according to a shortest path model of stratigraphic comparison based on the local matching cost matrix, screens out the minimum global matching cost in the global matching cost matrix by a dynamic waveform matching algorithm, backtracks each item accumulated on the obtaining path of the shortest global matching cost to obtain the shortest matching path, if stratigraphic units of two wells in the numerical value on the shortest path are in one-to-one correspondence, the stratigraphic units are mutually matched, if one stratigraphic unit of one well is matched with a plurality of stratums of the other well, the local matching cost of the plurality of strata is the smallest matched stratigraphic unit and the others are the missing stratigraphic units. In conclusion, the method integrates the information of the form similarity, the thickness, the depth and the like of the logging curves, judges the matching result through a dynamic waveform matching algorithm based on the geological knowledge that the difference between adjacent wells at a short distance is not large, and takes the shortest path corresponding to the minimum global matching cost as a matching path, so that the stratum comparison is more accurate.
The invention also relates to an intelligent stratum comparison system based on DTW, which corresponds to the intelligent stratum comparison method of the invention and can also be understood as a device for realizing the intelligent stratum comparison method of the invention, a first device, a second device and a third device which are connected in sequence are arranged, the devices work cooperatively, the second device can carry out variable point detection on normalized data obtained by the first device to carry out layering on a logging curve to obtain stratum units with different levels, the third device firstly extracts at least logging curve form similarity, depth, stratum thickness and mean value information of a comparison well, wherein the logging curve form similarity is obtained by a dynamic time warping algorithm, then calculates local matching cost between different stratum units of two wells to be compared by a dynamic waveform matching algorithm to establish a local matching cost matrix, obtaining a global matching cost matrix based on the local matching cost matrix, screening a minimum global matching cost value from the global matching cost matrix, backtracking from the minimum global matching cost value to obtain a shortest matching path, if the strata of the two wells are not lost, matching each stratum unit between the two wells one to one, corresponding to the two matched stratum units on each point on the shortest matching path, if the two wells are lost, matching one stratum unit of one well with a plurality of stratum units of the other well on the shortest matching path, wherein the matching principle is as follows: the method has the advantages that the matched stratum unit is used as the global matching cost, the missing stratum unit is used as the unmatched stratum unit, and the matching result is finally output.
Drawings
FIG. 1 is a flow diagram of a preferred embodiment of a DTW-based intelligent stratigraphic correlation method of the present invention;
FIG. 2 is a flow diagram of another preferred embodiment of a DTW-based intelligent stratigraphic correlation method of the present invention;
FIG. 3 is a graph of curves generated in a variable point detection process;
FIG. 4 is a schematic view of one embodiment of a well log after stratification;
FIG. 5 is a diagram illustrating an embodiment of a global matching cost matrix with labels;
FIG. 6 is a schematic diagram of an embodiment of a DTW-based intelligent stratigraphic correlation system of the present invention.
Reference numerals:
1-log curve; 2-a marker formation; 3-other strata.
Detailed Description
For a detailed description of the invention, reference will now be made to specific embodiments and accompanying drawings.
As shown in fig. 1, a DTW-based intelligent stratigraphic comparison method includes the following steps: the first step is as follows: acquiring original logging data and carrying out normalization preprocessing to form normalized logging data; the second step is as follows: extracting variable point information of the normalized logging data of each well by adopting a variable point detection algorithm, and layering logging curves to obtain stratum units of different levels; the third step: and extracting the respective logging curve characteristics of the comparison wells, wherein the curve characteristics at least comprise logging curve form similarity, depth, thickness and mean value information, the logging curve form similarity information is obtained through a dynamic time warping algorithm, the curve characteristics are calculated and processed through a dynamic waveform matching algorithm to determine a path pattern diagram and find out an optimal matching path, the optimal matching path is traced back, and stratum units are matched, whether stratum is lost or not is judged and output. Namely, in order to obtain a more accurate stratum comparison result for petroleum exploration and development, the invention extracts the logging curve form similarity of each stratum unit of the pre-compared A well and B well based on a dynamic time warping algorithm, fuses other conventional information, calculating the distance coefficient between the stratum units of the well A and the well B by a dynamic waveform matching algorithm to establish a local matching cost matrix, acquiring a global matching cost matrix, screening out the minimum global matching cost, obtaining the matching and missing results by backtracking the optimal matching path, considering the logging curve form similarity information during the judgment, during comparison, local and global are firstly carried out, and then the overall situation is reversely deduced to local, so that the optimal matching path is ensured to be obtained, the contrast well has the minimum difference and high matching degree, and the missing stratum unit is the unit which cannot be matched, so that the method is more accurate and has higher efficiency, and the interpretation of the stratum comparison result is stronger.
Preferably, a preferred embodiment of the DTW-based smart stratigraphic correlation method of the present invention is illustrated with reference to fig. 2. The method comprises the following steps:
s11: acquiring original logging data of different sources;
s12: carrying out normalization preprocessing on the original logging data to enable the numerical range of the logging data of each source to be distributed between [0,1] to form normalized data;
the normalization preprocessing mainly aims to solve the problems that the subsequent whole-region lithology prediction is influenced too much and the error is too big due to different numerical ranges of logging data results measured by different instruments, and the specific normalization preprocessing aims at the logging data of different sources, all the logging data are distributed in a range of [0,1], the maximum value and the minimum value of the whole data are not taken in the normalization process, but an accumulated probability distribution map is made for all the data, for example, preferably, the number accounting for 95% of the logging data of all the sources is firstly extracted as the maximum value, then the number accounting for 5% of the logging data of all the sources is extracted as the minimum value (of course, other accounting ratios can be extracted for probability distribution), then the normalization calculation formula is combined to normalize all the logging curve data by using the maximum value and the minimum value to obtain the normalization results of the logging data of all the sources respectively, so that the numerical range of the logging data of each source is distributed between [0,1], and the calculation formula of the normalization preprocessing is as follows:
where X represents the well log data to be normalized and X' represents the normalized well log data, the calculation process will traverse all of the well log data.
S2: extracting variable point information of the normalized logging data by adopting a variable point detection algorithm so as to stratify the logging curve of each well to obtain stratum units of different levels;
different normalized logging curves are combined into a plurality of layers by adopting a variable point detection algorithm based on a sliding window, the speed is high, the method is applicable to multivariable, and any single variable point detection algorithm can be expanded into a multi-variable point detection algorithm. The algorithm uses two windows that slide along the data stream. The statistical properties of the signal within each window are compared to a difference measure. For a given loss function c (), a difference metric d (), is derived:
d(yu..v,yv..w)＝c(yu..w)-c(yu..v)-c(yv..w) (2)
wherein { yt}tIs the input signal, u < v < w is the index, c (-) is the loss function, d (-) is a measure of the difference between the two windows.
The kernel function is selected as a loss function to project a low-dimensional linear inseparable and highly nonlinear logging signal into a high-dimensional regenerative Hilbert space, which is called reproducing Hilbert space in English and abbreviated as RKHS in English, so that the purpose of linear separability is achieved.
Given a semi-positive nucleus
And its mapping relation
H is a suitable Hilbert space, and our loss function detects the signal after projection { Φ (y)t)}tDefined as:
in formula (3), I is the region of interest,
is a signal { phi (y)t)}t∈IAs used herein, the kernel function is the radial basis kernel function (rbf):
k(x,y)＝exp(-γ||x-y||2) (4)
where | l | · | | is the euclidean norm, γ >0 is the so-called bandwidth parameter, determined from the median heuristic, i.e., the reciprocal equal to the median of all pairs of distances.
According to the following principle: if the sliding windows u.v. and v.w are located in the same layer, their statistical properties are similar and the difference between the two windows is small; if the sliding window is located at two different layers, the difference increases significantly, indicating that the boundary between the two windows is a variable point, defining the difference curve as:
(t,d(yt-w/2..t,yt..t+w/2)) (5)
wherein t is an index between w/2 and n-w/2, and n is the number of sample points; w is the sliding window length;
drawing a difference curve according to the relation that the difference measurement changes along with the data flow, as shown in fig. 3, continuing peak detection based on the difference curve, wherein the peak point corresponds to the change point of the original signal, namely the layer interface of the logging curve;
and repeating the above processes along the data stream until the variable point detection in the whole data stream in each well is completed, and layering the logging curves to obtain the stratigraphic units with different levels. As shown in fig. 4, for the layering result of the logging curve 1 of a part of signal sources in a well, the black vertical dotted line position is a variable point, the layer interface positions between the symbolic formation 2 and other formations 3 all have variable points in practice, and the layering effect is more accurate by detecting the variable points, wherein CALI represents a borehole diameter logging signal source, GR represents a natural gamma logging signal source, SP represents a natural potential logging signal source, RT represents a deep direction resistivity logging signal source, RI represents a shallow direction resistivity logging signal source, and of course, other signal sources can be included, and the logging curves of all the signal sources of one well need to be layered uniformly theoretically;
s31: extracting the logging curve form similarity of the contrast wells and at least depth, thickness and mean value information, wherein the logging curve form similarity is obtained through calculation of a dynamic time warping algorithm;
in addition to the curve features described above, other features such as mean square error, etc. may be selected.
(1) Depth f1
f1＝(y1+y2)/2 (6)
(2) Formation thickness f2
f2＝y2-y1 (7)
y 1: the top depth of any stratigraphic unit of each well, y 2: the stratum bottom depth of any stratum unit of each well;
(3) mean well log response f3
f3＝(a1+a2+…ai…+an)/n (8)
ai: logging curve values at the ith point;
(4) similarity f4 of curve form
Before the similarity of the two curves, the DTW algorithm is adopted in the embodiment to warp and distort one or both sequences under the time axis to achieve better alignment, and then the similarity between the two time sequencers is calculated.
Assuming that the time series for well a and well B are Q and C, respectively, their lengths are n and m, respectively: the value of each point in the sequence is the characteristic value of each frame in the sequence:
Q＝q1,q2,…,qi,…,qn；
C＝c1,c2,…,cj,…,cm；
to align the two sequences, we need to construct an n × m matrix grid, where the matrix element (i, j) represents the distance d (qi, cj) between two points qi and cj, i.e. the similarity between each point of the sequence Q and each point of C, and the smaller the distance is, the higher the similarity is, and generally, the euclidean distance d (qi, cj) ═ qi-cj is adopted2And may also be understood as a degree of distortion. Each matrix element (i, j) represents the alignment of points qi and cj. The DTW algorithm can be summarized as finding a path through a number of grid points in the grid, so that the distance is minimized, and the grid points through which the path passes are aligned points at which the two sequences are calculated.
We define this path as a warped path, and denoted by W, whose k-th element is defined as wk ═ k (i, j), defining a mapping of sequences Q and C:
W＝w1，w2，...，wk max(m，n)≤＝K＜m+n+1 (9)
this path is not chosen arbitrarily and needs to satisfy several constraints:
i boundary conditions: w1 (1,1) and wK (m, n), the change speed of the logging signals of different logging instruments can change, but the sequence of the parts cannot be changed, so the selected path is started from the lower left corner and ended at the upper right corner;
II continuity: if wk-1 ═ a ', b', then for the next point wk ═ a, b) of the path, it is necessary to satisfy (a-a ') < ═ 1 and (b-b') < ═ 1, i.e. it is impossible to cross a certain point to match, and it is only possible to align with its own neighboring point, which ensures that each coordinate in Q and C appears in W;
III monotonicity: if wk-1 ═ (a ', B'), then 0< ═ a 'and 0< ═ B' need to be satisfied for the next point of the path, which limits the points above W to have to be monotonic over time to ensure that the dashed lines in graph B do not intersect.
Combining continuity and monotonicity constraints, the path of each grid point has only three directions. For example, if the path has passed through lattice point (i, j), then the next passing lattice point may be only one of the following three cases: (i +1, j), (i, j +1) or (i +1, j +1), the paths that satisfy these constraints above can be exponential, and we need to be the paths that minimize the following regularized cost:
k in the denominator is mainly used to compensate for the different length regular paths. Here we define an accumulated distance. Starting from point (0,0), the two sequences Q and C are matched, and every time a point is reached, the distances calculated for all the previous points are accumulated. After reaching the end point (n, m), the cumulative distance is the last total distance we said above, i.e. the similarity of the curve shapes of the sequences Q and C.
The cumulative distance γ (i, j) can be expressed in the following way, where the cumulative distance γ (i, j) is the current lattice point distance d (i, j), i.e. the sum of the euclidean distance/similarity of points qi and cj and the cumulative distance of the smallest neighboring element that can reach the point:
f4＝γ(i，j)＝d(qi，cj)+min{γ(i-1，j-1)，γ(i-1，j)，γ(i，j-1)} (11)
s32: sequentially calculating the distance coefficient/local matching cost of each stratigraphic unit of the comparison well to establish a local matching cost matrix;
the local matching cost is calculated by the formula
d(A，b)＝sqrt{[w1×diff(f1)]2+[w2×diff(f2)]2+w3×diff(f3)]2+[w4×
diff(f4)]2) (12)
d (A, B) is a local matching cost and represents a distance coefficient between a logging curve of a stratigraphic unit of the well A and a logging curve of a stratigraphic unit of the well B; the weight corresponding to the ith attribute of wi is a set value; diff (i) the cost corresponding to the ith attribute is the absolute value of the difference of fi of the well A and the well B, and i is 1-3; diff (f4) is the DTW distance f4 of the curve.
According to the above formula, the obtained local matching cost matrix is shown in table 1. In table 1, the vertical direction represents the I-VII stratigraphic units of the a well, the horizontal direction represents the I-VII stratigraphic units of the B well, each point in the matrix represents the local matching cost of the I-VII stratigraphic units of the a well and the I-VII stratigraphic units of the B well, and the smaller the local matching cost value, the higher the matching degree of the two stratigraphic units. Of course, table 1 is only a form of local matching cost matrix, and the stratigraphic units in each well are arranged in series from I to VII, and it is also possible that the stratigraphic units of a and/or B lack a certain stratigraphic unit or units, and I to VII may be discontinuous.
TABLE 1 local matching cost matrix
S33: based on the local matching cost matrix, obtaining a global matching cost matrix through a dynamic waveform matching algorithm, and screening out the minimum global matching cost in the global matching cost matrix;
the global matching cost calculation formula is as follows:
D(Am，Bn)＝∑d(Ai，Bj)+∑g(Ak)+∑g(Bk) (13)
d (Am, Bn) is global matching cost, and Σ D (Ai, Bj) represents the sum of distance coefficients/local matching cost between all mutually matched stratigraphic units; k is the number of stratum deletions in the sequence, sigma g (Ak) represents the sum of distance coefficients of repeated matching of the missing stratum unit in the well A and the well B; Σ g (bk) represents the sum of the distance coefficients of the missing stratigraphic unit in the B-well that matches the a-well repeat.
The invention utilizes the shortest path problem in dynamic planning to simulate the process of stratum comparison, and uses the optimization algorithm of dynamic planning to complete the concrete calculation of stratum comparison, namely the minimization of distance coefficient, thereby carrying out stratum matching.
When the optimization result of the multi-stage decision process is solved by using a dynamic waveform algorithm, the optimization calculation of the distance coefficient is carried out in stages, namely, the optimization of the current stage is carried out on the basis of the optimization result of the previous stage, and the whole solving process of the well is a continuous recursion process.
According to the shortest path model of stratigraphic comparison, if the k stage is to complete the best matching of A1, A2 … Am and B1, B2 … Bn, the best matching is preferably obtained after adding one matching on the basis of the three states of the first stage, namely the first three points, and the three states of the k-1 stage are respectively:
state 1: at a point (Ai-1, Bj-1); state 2: at point (Ai-1, Bj); state 3: at a point (Ai, Bj-1); the distances from these three points to the point (Ai, Bj) are d (Ai, Bj), g (Ai), g (Bj), so the recursion formula in the k stage is:
D(Ai,Bj)＝min{D(Ai-1,Bj)+g(Ai),D(Ai-1,Bj-1)+d(Ai,Bj),D(Ai,Bj-1)+g(Bj)}
the best matching distance D (a, B) of the sequences a, B can be found according to the above formula, i.e. each point in the global matching cost is calculated by the above formula.
As shown in fig. 5, a global matching cost matrix is obtained according to a shortest path model by a dynamic waveform matching algorithm, and a path matrix is recorded in a distance calculation process, and an agreed mark is: 1-from the left; 2-from the top left; 3-from above.
For example, three points of the first stage in fig. 5:
288.2/1 indicates point 193.0 (well I matched well II) + 95.2 left (well I matched well I);
213.4/2 represents 118.2 points (a well II stratigraphic unit matches with B well I stratigraphic unit) + upper left 95.2 points (a well I stratigraphic unit matches with B well I stratigraphic unit);
210.5/3 represents 115.3(a well No. II stratigraphic unit matches with B well No. II stratigraphic unit) + 95.2 above (a well No. I stratigraphic unit matches with B well No. I stratigraphic unit);
on the basis of the three points, the corresponding values of the 7 th row and the 6 th row of the graph 6 are obtained as global matching cost values according to a shortest path model and the like, wherein 690.7/2 is the minimum global matching cost.
S34: backtracking the minimum global matching cost to obtain a shortest path, and matching the stratum units to judge whether a missing stratum exists or not and outputting;
as shown in FIG. 5, the trace-back path of the global minimum matching cost 690.7/2, represented by the reverse arrow, is:
690.7/2 (VII of A matches VII of B) → 618.2 (VI of A matches VI of B) → 550/2 (V of A matches V of B) → 407.7/2 (IV of A matches IV of B) → 315/2 (III of A matches III of B)
→ 210.5/3 (I match of a and B) → 95.5 (I match of a and B);
wherein, the stratigraphic units of two wells in each point value of 690.7/2, 618.2, 550/2, 407.7/2 and 315/2 correspond one to one, and VII-III of A and VII-III of B are matched with each other in sequence; and I of B is matched with II of A and I of A, wherein the local matching cost of I of B and I of A is 95.2 minimum, which means that I of B should be matched with I of A, and II of A is missing.
The invention also relates to an intelligent formation comparison system based on DTW, which corresponds to the intelligent formation comparison method of the invention and can also be understood as a device for realizing the intelligent formation comparison method of the invention, and as shown in FIG. 6, the intelligent formation comparison system comprises a first device, a second device and a third device which are connected in sequence. The first device comprises a data acquisition device and a normalization preprocessing device which are sequentially connected, wherein the data acquisition device receives original logging data and sends the original logging data to the normalization preprocessing device, and the normalization preprocessing device converts the original logging data from different sources into normalization logging data distributed in a [0,1] range. The second device comprises a variable point detection device and a layering device which are sequentially connected, wherein the variable point detection device comprises a data selection device, a difference characteristic calculation device, a curve generation device and a peak value detection device, the data selection device is connected with the normalization preprocessing device and used for receiving the normalized logging data and selecting two sliding windows with equal length along a data stream, the difference characteristic calculation device compares each statistical characteristic of the two sliding windows and calculates a difference metric value through a variable point detection algorithm, the curve generation device draws a difference curve of the difference metric along the data stream, the peak value detection device detects the peak value of the difference curve, the layering device is connected with the peak value detection device, and the logging curve is layered at each variable point to obtain stratum units with different levels.
The third device comprises a curve form similarity calculation device, a feature extraction device, a matching device, a deletion judgment device and an output device which are connected in sequence, wherein the matching device comprises a local matching cost matrix generation device, a global matching cost matrix generation device and a shortest path backtracking device, the curve form similarity calculation device calculates the logging curve form similarity between each stratum unit of two logging curves of two wells which are compared based on a dynamic time warping algorithm, the feature extraction device takes the logging curve form similarity and at least depth, stratum thickness and mean value information, the local matching cost matrix generation device calculates the distance coefficient of each stratum unit of the comparison wells in sequence to establish a local matching cost matrix, and the global matching cost matrix generation device is based on the local matching cost matrix, the method comprises the steps of obtaining a global matching cost matrix through a dynamic waveform matching algorithm, screening out the minimum global matching cost in the global matching cost matrix, backtracking the shortest matching path of the minimum global matching cost by the shortest path backtracking device, matching stratum units by backtracking the shortest matching path to judge whether a missing stratum exists or not, and outputting the matching result by the output device.
It should be noted that the above-mentioned embodiments enable a person skilled in the art to more fully understand the invention, without restricting it in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. An intelligent stratum contrast method based on DTW is characterized by comprising the following steps:
the first step is as follows: acquiring original logging data and carrying out normalization preprocessing to form normalized logging data;
the second step is as follows: extracting variable point information of the normalized logging data by adopting a variable point detection algorithm based on a sliding window so as to stratify the logging curve of each well to obtain stratigraphic units of different levels;
the third step: extracting the logging curve characteristics of the wells to be compared, wherein the logging curve characteristics at least comprise logging curve form similarity, depth, thickness and mean value information, and the logging curve form similarity information is obtained through a DTW algorithm; and calculating and processing the logging curve characteristics by a dynamic waveform matching algorithm to determine a matching path of the stratum, and backtracking the matching path to match stratum units so as to judge whether the stratum is missing or not and output.
2. The DTW-based smart stratigraphic correlation method of claim 1, wherein the third step comprises the steps of:
s31: extracting the logging curve form similarity of the wells to be compared and at least depth, thickness and mean value information, wherein the logging curve form similarity is obtained through calculation of a DTW algorithm;
s32: sequentially calculating the distance coefficient/local matching cost of each stratigraphic unit of the comparison well to establish a local matching cost matrix;
s33: based on the local matching cost matrix, obtaining a global matching cost matrix through a dynamic waveform matching algorithm, and screening out the minimum global matching cost in the global matching cost matrix;
s34: and backtracking the minimum global matching cost to obtain a shortest path, and matching the stratum units according to a judgment criterion to judge whether a missing stratum exists or not and outputting.
3. The DTW-based smart stratigraphic correlation method of claim 1, characterized in that the first step comprises the steps of: for the logging data of different sources, firstly, 95% of the logging data of each source is respectively extracted as the maximum value, 5% of the logging data of each source is extracted as the minimum value, and then the normalized logging data of the logging data of each source is respectively obtained by combining a normalized calculation formula, so that the numerical range of the logging data of each source is distributed between [0,1 ].
4. The DTW-based smart stratigraphic correlation method of claim 1, wherein the second step comprises the steps of: selecting two sliding windows with equal length along the data stream, and comparing each statistical characteristic of the two sliding windows through a variable point detection algorithm to obtain difference measurement; drawing a difference curve according to the relation between the difference measurement and the data stream; and detecting the peak value of the difference curve, repeating the process along the data flow until the variable point detection in all the data flows in each well is completed, and layering the logging curve at each variable point to obtain the stratigraphic units with different levels.
5. The DTW-based smart formation mapping method of claim 4, wherein the variation point detection algorithm calculates the difference metric as the difference between the loss function in two selected sliding windows and the loss function of each sliding window individually, and the loss function detects the mean change of the signal projected by the Gaussian function to the high-dimensional regenerated Hilbert space.
6. An intelligent stratum contrast system based on DTW is characterized by comprising a first device, a second device and a third device which are connected in sequence,
the first device is used for acquiring original logging data and carrying out normalization preprocessing to form normalized logging data;
the second device extracts the variable point information of the normalized logging data by adopting a variable point detection algorithm based on a sliding window so as to stratify the logging curve of each well and obtain stratigraphic units of different levels;
the third device extracts the logging curve characteristics of the wells to be compared, wherein the logging curve characteristics at least comprise logging curve form similarity, depth, thickness and mean value information, and the logging curve form similarity information is obtained through a DTW algorithm; and calculating and processing the logging curve characteristics by a dynamic waveform matching algorithm to determine a matching path, and backtracking the matching path to match the stratum units so as to judge whether a missing stratum exists and output.
7. The DTW-based intelligent stratigraphic comparison system of claim 6, wherein the first device comprises a data acquisition device and a normalization pre-processing device which are connected in sequence, the data acquisition device receives the raw logging data and sends the raw logging data to the normalization pre-processing device, and the normalization pre-processing device converts the raw logging data from different sources into the normalized logging data distributed in the range of [0,1 ].
8. The DTW-based intelligent formation comparison system of claim 7, wherein the second device comprises a variable point detection device and a layering device connected in sequence, the variable point detection device comprises a data selection device, a difference characteristic calculation device, a curve generation device and a peak detection device connected in sequence, the data selection device is connected to the normalization preprocessing device and is used for receiving the normalized logging data and selecting two sliding windows with equal length along the data stream, the difference characteristic calculation device compares each statistical characteristic of the two sliding windows and calculates a difference metric value through a variable point detection algorithm, the curve generation device plots the difference metric along the data stream to form a difference curve, the peak detection device detects the peak value of the difference curve, and the layering device is connected to the peak detection device, and layering the logging curves at each variable point to obtain different levels of stratigraphic units.
9. The DTW-based intelligent formation comparison system as claimed in claim 8, wherein the third device comprises a curve form similarity calculation device, a feature extraction device, a matching device, a loss judgment device and an output device, which are connected in sequence, the curve form similarity calculation device is connected with the layering device, the DTW algorithm is used to calculate the logging curve form similarity between any two formation units of the two logging curves to be compared, the feature extraction device extracts the logging curve form similarity and at least depth, formation thickness and mean value information of each formation unit of the two logging curves to be compared, the matching device sequentially calculates the distance coefficient/local matching cost of each formation unit of the comparison well to establish a local matching cost matrix, and based on the local matching cost matrix, obtaining a global matching cost matrix through a dynamic waveform matching algorithm, screening out the minimum global matching cost in the global matching cost matrix, backtracking the minimum global matching cost to obtain a shortest path, matching the stratum units by the loss judgment device to judge whether a lost stratum exists or not, and outputting a result by the output device.
10. The DTW-based intelligent formation comparison system according to claim 9, wherein the matching device comprises a local matching cost matrix generation device, a global matching cost matrix generation device, and a shortest path backtracking device, which are connected in sequence, the local matching cost matrix generation device calculates the distance coefficient/local matching cost of each formation unit of the comparison well in sequence to establish a local matching cost matrix, the global matching cost matrix generation device obtains a global matching cost matrix through a dynamic waveform matching algorithm based on the local matching cost matrix, a minimum global matching cost is screened out from the global matching cost matrix, and the shortest path backtracking device backtracks the shortest matching path of the minimum global matching cost to determine whether there is a missing formation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910785222.1A CN110852144A (en) | 2019-08-23 | 2019-08-23 | DTW-based intelligent stratum comparison method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910785222.1A CN110852144A (en) | 2019-08-23 | 2019-08-23 | DTW-based intelligent stratum comparison method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110852144A true CN110852144A (en) | 2020-02-28 |
Family
ID=69595531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910785222.1A Pending CN110852144A (en) | 2019-08-23 | 2019-08-23 | DTW-based intelligent stratum comparison method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852144A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420936A (en) * | 2021-07-01 | 2021-09-21 | 中国海洋石油集团有限公司 | Stratum comparison method based on dynamic time programming optimization algorithm |
| CN113777669A (en) * | 2021-08-17 | 2021-12-10 | 中国石油化工股份有限公司 | Sandstone reservoir sublayer comparison method based on dynamic time sequence matching number technology |
| CN114909125A (en) * | 2022-06-08 | 2022-08-16 | 中国地质大学（北京） | Text type rock debris logging data numeralization and stratum automatic comparison method and device |
| CN115113299A (en) * | 2022-05-18 | 2022-09-27 | 北京月新时代科技股份有限公司 | Intelligent marking stratum positioning and dividing method, device, equipment and storage medium |
| CN115113281A (en) * | 2022-05-18 | 2022-09-27 | 北京月新时代科技股份有限公司 | Method, device, equipment and storage medium for determining marker well and marker layer thereof |
| WO2022203702A1 (en) * | 2021-03-26 | 2022-09-29 | Schlumberger Technology Corporation | Wellbore data depth matching using change point algorithms |
| CN117910883A (en) * | 2024-03-18 | 2024-04-19 | 中海油田服务股份有限公司 | Logging data quality detection method, device, computing equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150088424A1 (en) * | 2013-09-20 | 2015-03-26 | Schlumberger Technology Corporation | Identifying geological formation depth structure using well log data |
| CN105426645A (en) * | 2016-01-12 | 2016-03-23 | 东营文迪科技有限公司 | Automatic comparing method and system for ASC stratum |
| CN106707344A (en) * | 2016-12-12 | 2017-05-24 | 中国石油天然气股份有限公司 | Stratum sequence dividing method and device |
| CN107218033A (en) * | 2017-05-15 | 2017-09-29 | 中国海洋石油总公司 | A kind of inversion method for the method and formation parameter for recognizing attitude of stratum |
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
-
2019
- 2019-08-23 CN CN201910785222.1A patent/CN110852144A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150088424A1 (en) * | 2013-09-20 | 2015-03-26 | Schlumberger Technology Corporation | Identifying geological formation depth structure using well log data |
| CN105426645A (en) * | 2016-01-12 | 2016-03-23 | 东营文迪科技有限公司 | Automatic comparing method and system for ASC stratum |
| CN106707344A (en) * | 2016-12-12 | 2017-05-24 | 中国石油天然气股份有限公司 | Stratum sequence dividing method and device |
| CN107218033A (en) * | 2017-05-15 | 2017-09-29 | 中国海洋石油总公司 | A kind of inversion method for the method and formation parameter for recognizing attitude of stratum |
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
Non-Patent Citations (6)
| Title |
|---|
| CHARLES TRUONG等: "Selective review of offline change point detection methods", 《ARXIV PREPRINT ARXIV》 * |
| EAMONN J. KEOGH等: "Derivative Dynamic Time Warping", 《PROCEEDINGS OF THE 2001 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM)》 * |
| 吴志芳等: "动态模式匹配算法在地层对比中的应用", 《世界地质》 * |
| 张子戎等, 北京：煤炭工业出版社 * |
| 杨洁等: "动态时间规则DTW算法的研究", 《科技与创新》 * |
| 蔡希源等: "《陆相盆地高精度层序地层学 隐蔽油气藏勘探基础、方法与实践 技术方法篇》", 31 May 2004, 《北京：地质出版社》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022203702A1 (en) * | 2021-03-26 | 2022-09-29 | Schlumberger Technology Corporation | Wellbore data depth matching using change point algorithms |
| CN113420936A (en) * | 2021-07-01 | 2021-09-21 | 中国海洋石油集团有限公司 | Stratum comparison method based on dynamic time programming optimization algorithm |
| CN113420936B (en) * | 2021-07-01 | 2022-12-20 | 中国海洋石油集团有限公司 | Stratum comparison method based on dynamic time programming optimization algorithm |
| CN113777669A (en) * | 2021-08-17 | 2021-12-10 | 中国石油化工股份有限公司 | Sandstone reservoir sublayer comparison method based on dynamic time sequence matching number technology |
| CN115113299A (en) * | 2022-05-18 | 2022-09-27 | 北京月新时代科技股份有限公司 | Intelligent marking stratum positioning and dividing method, device, equipment and storage medium |
| CN115113281A (en) * | 2022-05-18 | 2022-09-27 | 北京月新时代科技股份有限公司 | Method, device, equipment and storage medium for determining marker well and marker layer thereof |
| CN114909125A (en) * | 2022-06-08 | 2022-08-16 | 中国地质大学（北京） | Text type rock debris logging data numeralization and stratum automatic comparison method and device |
| CN114909125B (en) * | 2022-06-08 | 2024-08-16 | 中国地质大学（北京） | Text type rock debris logging data numeralization and stratum automatic comparison method and device |
| CN117910883A (en) * | 2024-03-18 | 2024-04-19 | 中海油田服务股份有限公司 | Logging data quality detection method, device, computing equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852144A (en) | DTW-based intelligent stratum comparison method and system | |
| Akinnikawe et al. | Synthetic well log generation using machine learning techniques | |
| CN109061765B (en) | Trap evaluation method for heterogeneous thin sandstone interbed reservoir | |
| US20220170366A1 (en) | 3d in-situ characterization method for heterogeneity in generating and reserving performances of shale | |
| US20040133531A1 (en) | Neural network training data selection using memory reduced cluster analysis for field model development | |
| Alnahwi et al. | Mineralogical composition and total organic carbon quantification using x-ray fluorescence data from the Upper Cretaceous Eagle Ford Group in southern Texas | |
| CN106842307B (en) | Reservoir stratum fine prediction method based on waveform classification and retrieval under forward constraint | |
| CN108931814A (en) | A method of the basement rock FRACTURE PREDICTION based on the fusion of more attributes | |
| US20140222347A1 (en) | Seismic Waveform Classification System And Method | |
| CN102176052B (en) | Hierarchical sequence analysis method oriented to generation of three-dimensional hierarchical grids | |
| CN104011566A (en) | Wavelet-transform based system and method for analyzing characteristics of a geological formation | |
| Cooper et al. | Quantitative biostratigraphy of the Taranaki Basin, New Zealand: A deterministic and probabilistic approach | |
| US20150219779A1 (en) | Quality control of 3d horizon auto-tracking in seismic volume | |
| WO2012125357A2 (en) | Subsurface directional equalization analysis of rock bodies | |
| CN109763814B (en) | Stratum matching visual analysis method based on multi-dimensional logging data | |
| Konoshonkin et al. | Machine learning clustering of reservoir heterogeneity with petrophysical and production data | |
| CN117150929B (en) | Deep oil gas accurate navigation well earthquake combined clastic rock lithology model updating system | |
| Irofti et al. | Characterization of a Tight Gas Reservoir Using the Integration of Electrofacies and Fracture Aperture, Ahnet, Algeria | |
| EP3387469B1 (en) | Electrofacies determination | |
| CN115494552A (en) | Method for correcting logging curve of inclined well and application thereof | |
| CN112287532A (en) | Edge-controlled seismic driving modeling method | |
| CN110795513B (en) | Method for predicting distribution of river facies source storage ectopic type compact oil gas dessert area | |
| US10996357B2 (en) | Downhole interpretation techniques using borehole dips | |
| US11397278B2 (en) | Determining a numerical age for geological events within a scheme | |
| CN114167496B (en) | Method for establishing variable speed average speed field in complex construction area |
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: 20200228 |