CN111751878A - Method and device for predicting transverse wave velocity - Google Patents
Method and device for predicting transverse wave velocity Download PDFInfo
- Publication number
- CN111751878A CN111751878A CN202010434118.0A CN202010434118A CN111751878A CN 111751878 A CN111751878 A CN 111751878A CN 202010434118 A CN202010434118 A CN 202010434118A CN 111751878 A CN111751878 A CN 111751878A
- Authority
- CN
- China
- Prior art keywords
- curve
- wave velocity
- learning rate
- neural network
- transverse wave
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000012549 training Methods 0.000 claims abstract description 91
- 238000003062 neural network model Methods 0.000 claims abstract description 72
- 238000010606 normalization Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000012360 testing method Methods 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 19
- 230000004913 activation Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 238000005315 distribution function Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 15
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 22
- 239000011435 rock Substances 0.000 description 14
- 238000004088 simulation Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 229910052500 inorganic mineral Inorganic materials 0.000 description 4
- 239000011707 mineral Substances 0.000 description 4
- 239000012530 fluid Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008021 deposition Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002637 fluid replacement therapy Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000004257 Cordia myxa Nutrition 0.000 description 1
- 244000157795 Cordia myxa Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000010453 quartz Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000003079 shale oil Substances 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/303—Analysis for determining velocity profiles or travel times
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/40—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Geology (AREA)
- Geophysics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Environmental & Geological Engineering (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a method and a device for predicting transverse wave velocity, wherein the method comprises the following steps: acquiring a conventional logging curve and a known well transverse wave velocity curve; determining a preferred curve according to a conventional logging curve and a known transverse wave velocity curve; carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization; establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well shear wave speed, and determining a shear wave speed prediction model; and inputting the normalized optimal curve into a transverse wave velocity prediction model to determine the transverse wave velocity. In the whole prediction process of the transverse wave velocity, only a known well transverse wave velocity curve and a conventional logging curve of a pre-logging well are needed, the transverse wave velocity is accurately predicted directly from data, the adjustment parameters are few, the requirement on personnel is low, and the method can be widely applied to actual production.
Description
Technical Field
The invention relates to the technical field of geophysical, in particular to a method and a device for predicting transverse wave velocity.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The transverse wave velocity is used as an important parameter in fluid replacement, prestack forward modeling and inversion, and in the seismic forward modeling process, the accuracy of the result directly influences the result after subsequent fluid replacement, so that the understanding of geophysicists on elastic parameters and seismic response change rules under different fluid saturation conditions is influenced; in the seismic prestack inversion process, due to the fact that low-frequency information is lost in the earthquake, a low-frequency model is obtained through interpolation and extrapolation of logging, and the low-frequency model controls the whole deposition background and deposition rule of a research area, the accuracy of transverse wave speed on logging also influences the whole prestack inversion result, and the importance of transverse wave speed prediction is reflected. In unconventional reservoirs such as shale gas, compact oil and the like, stratum parameters such as stratum stress, stratum pressure and the like can be calculated only under the condition that the transverse wave velocity is accurate. Therefore, the shear wave velocity plays a crucial role in the prediction and evaluation of conventional and unconventional oil and gas reservoir parameters.
The conventional method for predicting the shear wave velocity by using logging information mainly comprises an empirical formula method and a rock physical modeling method. The empirical formula method is usually a unit or multiple linear regression method to establish the functional relationship between the transverse wave velocity curve and the conventional logging curves such as gamma, neutron, longitudinal wave time difference and the like, and the fitting function is usually too simple, so that the precision is difficult to meet the production requirement. In recent years, many domestic and foreign scholars develop a rock physics modeling method for predicting transverse waves, the method needs to accurately evaluate the stratum, has high requirements on seismic reservoir prediction workers, needs to evaluate key parameters such as mineral content, porosity and the like which meet the rock physics modeling requirements, and also needs to evaluate TOC, gas content and the like in shale oil. And the input skeleton parameters are numerous, 8 parameters are involved under the condition of two minerals, 4 parameters are added when one mineral is added subsequently, and the parameters such as the property, the temperature, the pressure and the like of formation fluid are difficult to obtain, so that in the rock physical simulation process of the unconventional reservoir such as compact oil, because the input parameters are numerous, a parameter which accords with the condition of an actual work area is difficult to obtain preferentially, a lot of difficulties also occur in the actual operation process, and the prediction precision is poor.
Vp/Vs calculated by a linear fitting method through an empirical formula is basically a constant and cannot meet the requirements of high-precision AVO forward modeling and prestack elastic parameter inversion.
The existing rock physical modeling method has the defects that the adjustable parameters are numerous, some parameters are difficult to obtain, the flow is complex, operators are required to have professional backgrounds of well logging explanation and seismic rock physical modeling, and the method is difficult to popularize and apply in actual production.
Therefore, how to provide a new solution, which can solve the above technical problems, is a technical problem to be solved in the art.
Disclosure of Invention
The embodiment of the invention provides a method for predicting transverse wave velocity, which directly starts from data to realize accurate prediction of the transverse wave velocity, and comprises the following steps:
acquiring a conventional logging curve and a known well transverse wave velocity curve;
determining a preferred curve according to a conventional logging curve and a known transverse wave velocity curve;
carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization;
establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well shear wave speed, and determining a shear wave speed prediction model;
and inputting the normalized optimal curve into a transverse wave velocity prediction model to determine the transverse wave velocity.
The embodiment of the present invention further provides a device for predicting a shear wave velocity, including:
the data acquisition module is used for acquiring a conventional logging curve and a known well transverse wave velocity curve;
the optimal curve determining module is used for determining an optimal curve according to the conventional logging curve and the known well transverse wave velocity curve;
the normalization module is used for performing normalization processing on the optimized curve and determining the optimized curve after normalization;
the transverse wave velocity prediction model determining module is used for establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well transverse wave velocity and determining a transverse wave velocity prediction model;
and the transverse wave velocity determining module is used for inputting the normalized optimal curve into the transverse wave velocity prediction model to determine the transverse wave velocity.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for predicting the shear wave velocity when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the method for predicting a shear wave velocity described above.
According to the method and the device for predicting the shear wave velocity, provided by the embodiment of the invention, a conventional logging curve is optimized on the basis of a known well shear wave velocity curve, an optimized curve is determined, normalization processing is carried out, a depth feedforward neural network model is established by combining the conventional logging curve on the basis, the known well shear wave velocity is used for training, a shear wave velocity prediction model is determined, and finally the optimized curve after normalization is input into the shear wave velocity prediction model to determine the shear wave velocity; in the whole prediction process of the transverse wave velocity, only a known well transverse wave velocity curve and a conventional logging curve of a pre-logging well are needed, the transverse wave velocity is accurately predicted directly from data, adjusting parameters are few, requirements for personnel are low, and the method can be widely applied to actual production.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic diagram of a method for predicting a shear wave velocity according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for predicting shear wave velocity according to an embodiment of the present invention.
Fig. 3 is a comparison diagram of the transverse wave time difference obtained by the transverse wave velocity prediction method, the transverse wave time difference obtained by rock physical simulation, and the transverse wave time difference obtained by an empirical formula according to the embodiment of the present invention.
Fig. 4 is a schematic diagram of the transverse wave time difference error obtained by an empirical formula.
FIG. 5 is a schematic diagram of the transverse wave time difference error obtained by rock physics simulation.
Fig. 6 is a schematic diagram of a transverse wave time difference error obtained by using a method for predicting a transverse wave velocity according to an embodiment of the present invention.
FIG. 7 is a schematic diagram of a computer device for implementing a method for predicting shear wave velocity according to the present invention.
Fig. 8 is a schematic diagram of a device for predicting a shear wave velocity according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Fig. 1 is a schematic diagram of a method for predicting a shear wave velocity according to an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a method for predicting a shear wave velocity, which implements accurate prediction of a shear wave velocity, and includes:
step 101: acquiring a conventional logging curve and a known well transverse wave velocity curve;
step 102: determining a preferred curve according to a conventional logging curve and a known transverse wave velocity curve;
step 103: carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization;
step 104: establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well shear wave speed, and determining a shear wave speed prediction model;
step 105: and inputting the normalized optimal curve into a transverse wave velocity prediction model to determine the transverse wave velocity.
According to the method for predicting the shear wave velocity provided by the embodiment of the invention, a conventional logging curve is optimized on the basis of a known well shear wave velocity curve, an optimized curve is determined, normalization processing is carried out, a depth feedforward neural network model is established by combining the conventional logging curve on the basis, the known well shear wave velocity is used for training, a shear wave velocity prediction model is determined, and finally the optimized curve after normalization is input into the shear wave velocity prediction model to determine the shear wave velocity; in the whole prediction process of the transverse wave velocity, only a known well transverse wave velocity curve and a conventional logging curve of a pre-logging are needed, the data is directly started, the adjusting parameters are few, the requirement on personnel is low, and the method can be widely applied to actual production.
Aiming at the problems that the conventional rock physical modeling needs a plurality of framework parameters to be adjusted, a high-precision prediction result of the transverse wave speed needs to be obtained, the estimation of mineral content, porosity and fluid content needs to be performed at a high precision in the early stage, the corresponding parameter adjusting work is complicated, high requirements are put forward to personnel in the parameter adjusting process, the threshold is high, and the method is difficult to popularize and apply in practical production and application. In view of the foregoing problems, an embodiment of the present invention provides a method for predicting a shear wave velocity, which includes:
acquiring a conventional logging curve and a known well transverse wave velocity curve; determining a preferred curve according to a conventional logging curve and a known transverse wave velocity curve; carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization; establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well shear wave speed, and determining a shear wave speed prediction model; and inputting the normalized optimal curve into a transverse wave velocity prediction model to determine the transverse wave velocity.
In the embodiment, the conventional logging curve is obtained from well data of which the shear wave speed is to be predicted, and the conventional logging data belongs to basic data in the exploration and development process and is easy to obtain; the known well shear velocity curve comprises actually measured shear velocity curves of a plurality of known wells, and can be obtained from a few existing array acoustic logging data.
In one embodiment, when the method for predicting shear wave velocity provided by the embodiment of the present invention is implemented, determining a preferred curve according to a conventional logging curve and a known well shear wave velocity curve includes:
and according to a vector correlation calculation method, calculating a correlation coefficient between the conventional logging curve and the known well transverse wave velocity curve, and performing correlation coefficient matrix evaluation on the conventional logging curve according to the correlation coefficient to determine a preferred curve.
In the embodiment, a conventional logging curve (as an input curve) is optimized, correlation coefficients between the conventional logging curve and a known well transverse wave velocity curve are calculated according to a vector correlation calculation method, the conventional logging curve and the known well transverse wave velocity curve are automatically sequenced according to the correlation coefficients, the conventional logging curve is subjected to correlation coefficient matrix evaluation according to the correlation coefficients, and an optimized curve is determined.
The foregoing conventional log, comprising: a combination of at least one or more of a gamma curve, a neutron curve, a density curve, and a sonic curve.
In a specific implementation of the method for predicting a shear wave velocity according to an embodiment of the present invention, in an embodiment, the normalizing the preferred curve to determine the normalized preferred curve includes:
fitting the statistical distribution characteristics of the optimal curve by adopting a Gaussian distribution function, and determining the mean value and the variance of the optimal curve;
and carrying out normalization processing on the preferred curves according to the mean value and the variance of the preferred curves, and determining the normalized preferred curves.
In an embodiment of the present invention, when the method for predicting a shear wave velocity is implemented specifically, a normalized preferred curve is determined as follows:
wherein x' is a normalized preferred curve; x is a preferred curve; μ is the mean of the preferred curves; σ is the variance of the preferred curve.
The above mentioned expression for determining the normalized preferred curve is for illustration, and it will be understood by those skilled in the art that the above formula may be modified in certain forms and other parameters or data may be added or other specific formulas may be provided according to the needs, and such modifications are all within the scope of the present invention.
In a specific implementation of the method for predicting shear wave velocity according to the embodiment of the present invention, in an embodiment, a deep feedforward neural network model is established in combination with a conventional well log, and training is performed by using a known well shear wave velocity to determine a shear wave velocity prediction model, including:
establishing a depth feedforward neural network model by combining a conventional logging curve, dividing known well transverse wave speeds into a training set and a testing set, optimizing an activation function, and selecting the activation function with smaller training errors and testing errors;
selecting a learning rate by adopting a dichotomy method, and determining a global optimal value of the deep feedforward neural network model;
randomly initializing a weight matrix, inputting a training set and a test set into a deep feedforward neural network model, training the deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of the training set and the test set;
when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again;
when the error between the training set and the testing set reaches a set value, the model is stored;
and (4) connecting the stored models in parallel, averaging, and determining a transverse wave velocity prediction model.
In a specific implementation of the method for predicting the shear wave velocity according to the embodiment of the present invention, in an embodiment, a dichotomy is used to select a learning rate and determine a global optimal value of a deep feedforward neural network model, including:
selecting a first learning rate to train the deep feedforward neural network model, and observing a training error of the first learning rate; meanwhile, a second learning rate is selected to train the deep feedforward neural network model, and a training error of the second learning rate is observed; wherein the first learning rate is greater than the second learning rate
Taking the midpoint of the first learning rate and the second learning rate as a midpoint learning rate, training the deep feedforward neural network model, and determining a midpoint learning rate training error;
judging whether the deep feedforward neural network model converges or not according to the training error of the first learning rate, the training error of the second learning rate and the training error of the midpoint learning rate;
and if the deep feedforward neural network model is not converged, the midpoint is taken from the midpoint learning rate to the direction of the second learning rate again until the deep feedforward neural network model is converged, and the global optimum value of the deep feedforward neural network model is determined.
In an embodiment, the deep feedforward neural network model established by combining the conventional well logging curves may be a multilayer learning network composed of fully-connected layers; in order to train the deep feedforward neural network model, known well transverse wave velocity is split into a training set and a testing set, and the training sets are respectively input into the deep feedforward neural network model for training; during training, different activation functions may be suitable for fitting the shear wave velocities of different work areas, and in the process, the current activation functions such as relu, elu, leak-relu, selu, gelu and the like need to be optimized, and the activation functions corresponding to smaller training errors and smaller testing errors are optimized. Then, selecting a learning rate by adopting a dichotomy method, and determining a global optimal value of the deep feedforward neural network model, wherein the method comprises the following steps: firstly, selecting a first learning rate to train a deep feedforward neural network model, and observing a training error of the first learning rate; meanwhile, a second learning rate is selected to train the deep feedforward neural network model, and a training error of the second learning rate is observed; after the training error of the first learning rate and the training error of the second learning rate are obtained, taking the midpoint of the first learning rate and the second learning rate as the midpoint learning rate, training the deep feedforward neural network model, and determining the midpoint learning rate training error; if the deep feedforward neural network model is not converged, the midpoint is taken from the midpoint learning rate to the direction of the second learning rate again until the deep feedforward neural network model is converged, and the global optimum value of the deep feedforward neural network model is determined, so that the efficiency in calculation can be ensured, and the global optimum value can be quickly searched. The first learning rate may be a larger learning rate when implemented, and the second learning rate may be a smaller learning rate. In an example, the first learning rate may be 110% to 500%, and the second learning rate may be 5% to 95%, when implemented, the first learning rate may be further narrowed according to actual requirements, for example, multiple choices of one or other values between 110%, 120%, 130%, 140%, and 150%; the second learning rate can also be increased according to actual requirements, for example, multiple choices of one or other values between 5%, 10%, 15%, 20%, 25%. 90%, 95% and the like are selected. Secondly, randomly initializing a weight matrix, training a deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of a training set and a testing set; when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again; when the error between the training set and the testing set reaches a set value, the model is stored; at this point, multiple models are saved; and connecting the stored multiple models in parallel, averaging and determining the transverse wave velocity prediction model.
Fig. 2 is a flowchart of a method for predicting shear wave velocity according to an embodiment of the present invention, and as shown in fig. 2, the process of predicting shear wave velocity includes:
inputting a curve; the input curve comprises an input conventional logging curve;
processing the input curve through the evaluation of the correlation coefficient matrix to determine an optimal curve;
carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization;
constructing a deep learning network by combining a conventional logging curve; the deep learning network comprises a deep feedforward neural network model;
randomly initializing a weight matrix, inputting a training set and a test set into a deep feedforward neural network model, training the deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of the training set and the test set;
judging the error between the training set and the test set;
when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again;
when the error between the training set and the testing set reaches a set value, the model is stored, and finally a plurality of models can be obtained: model 1, model 2 … … model n;
the stored n models are connected in parallel and averaged to determine a transverse wave velocity prediction model;
and inputting the normalized optimal curve into a transverse wave velocity prediction model to predict the transverse wave velocity.
According to the embodiment of the invention, a conventional logging curve is utilized, different learning models are constructed by adopting a deep learning algorithm, and the different models are connected in parallel to predict the transverse wave velocity, so that the transverse wave velocity prediction precision is improved. On the basis of similarity matrix evaluation of an input conventional logging curve, the logging curve most related to transverse wave speed is selected as a preferred curve, a deep feedforward neural network is constructed by combining the conventional logging curve on the basis, different prediction models are obtained by randomly initializing different weight coefficient matrixes, in the model training and testing process, models with high prediction precision are reserved by monitoring curves (error curves) formed by errors of a training set and a testing set, and finally the different models with high precision are connected in parallel to further improve the prediction precision. On the basis of the result of the inaccurate logging stratum evaluation, the conventional logging curve is directly utilized to predict the transverse wave speed, the model is optimized by only utilizing the error curve, and the method has the advantages of few intermediate steps, few adjustable parameters and easy development of large-scale application and operation.
According to the method for predicting the transverse wave velocity, the actual prediction results of a plurality of gas fields in the Sichuan basin and the Ordos basin show that the method has the advantages of high accuracy of the predicted transverse wave velocity and convenience in operation.
Fig. 3 is a comparison diagram of the transverse wave time difference obtained by the transverse wave velocity prediction method, the transverse wave time difference obtained by rock physical simulation, and the transverse wave time difference obtained by an empirical formula according to the embodiment of the present invention. In fig. 3, CAL is a well diameter curve, GR is a natural gamma curve, RT is a deep resistivity curve, RXO is a shallow resistivity curve, vdcl is a clay content, Vqua is a quartz content, port is a total porosity, cnl is a neutron curve, den is a density curve, dtc is a longitudinal wave time difference curve, DTS _ emp is a transverse wave time difference curve (reciprocal of transverse wave velocity) calculated by an empirical formula, DTS _ RM is a transverse wave time difference curve obtained by rock physical modeling, KERAS _ DTS is a transverse wave time difference curve obtained by using the present invention, and DTS is an actually measured transverse wave time difference curve.
FIG. 4 is a schematic diagram of a transverse wave time difference error obtained by an empirical formula; FIG. 5 is a schematic diagram of the transverse wave time difference error obtained by rock physics simulation; fig. 6 is a schematic diagram of a transverse wave time difference error obtained by using a method for predicting a transverse wave velocity according to an embodiment of the present invention; with reference to fig. 3 to fig. 6, it can be seen that the transverse wave time difference error obtained by using the method for predicting the transverse wave velocity according to the embodiment of the present invention is much smaller than the transverse wave time difference error obtained by using an empirical formula and the transverse wave time difference error obtained by using rock physical simulation; furthermore, the shear wave velocity obtained by the method for predicting the shear wave velocity according to the embodiment of the invention is used for calculating the velocity ratio of the shear wave (VpVs _ DL), and the error of the measured velocity ratio of the shear wave (VpVs) is smaller than that of the velocity ratio of the shear wave (VpVs _ emp) predicted by an empirical formula and the velocity ratio of the shear wave (VpVs _ RM) obtained by rock physics modeling, wherein the error is less than 3%, and the errors of the other methods are close to 10%.
Fig. 7 is a schematic diagram of a computer device for executing a method for predicting a shear wave velocity according to an embodiment of the present invention, and as shown in fig. 7, an embodiment of the present invention further provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for predicting a shear wave velocity when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the method for predicting a shear wave velocity described above.
The embodiment of the invention also provides a device for predicting the transverse wave velocity, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to a method for predicting the transverse wave velocity, the implementation of the device can refer to the implementation of the method for predicting the transverse wave velocity, and repeated parts are not repeated.
Fig. 8 is a schematic diagram of a device for predicting a shear wave velocity according to an embodiment of the present invention, and as shown in fig. 8, a device for predicting a shear wave velocity according to an embodiment of the present invention may include:
a data acquisition module 801, configured to acquire a conventional logging curve and a known well shear velocity curve;
a preferred curve determination module 802 for determining a preferred curve based on the conventional well log curve and the known well shear velocity curve;
a normalization module 803, configured to perform normalization processing on the preferred curve, and determine a normalized preferred curve;
the transverse wave velocity prediction model determining module 804 is used for establishing a depth feedforward neural network model by combining a conventional logging curve, training by using the known well transverse wave velocity and determining a transverse wave velocity prediction model;
and a shear wave velocity determination module 805, configured to input the normalized preferred curve into a shear wave velocity prediction model to determine a shear wave velocity.
In an embodiment of the invention, when the apparatus for predicting a shear wave velocity provided by the embodiment of the present invention is implemented, the preferable curve determining module is specifically configured to:
and according to a vector correlation calculation method, calculating a correlation coefficient between the conventional logging curve and the known well transverse wave velocity curve, and performing correlation coefficient matrix evaluation on the conventional logging curve according to the correlation coefficient to determine a preferred curve.
In an embodiment of the present invention, when the apparatus for predicting a shear wave velocity is implemented, the normalization module is specifically configured to:
fitting the statistical distribution characteristics of the optimal curve by adopting a Gaussian distribution function, and determining the mean value and the variance of the optimal curve;
and carrying out normalization processing on the preferred curves according to the mean value and the variance of the preferred curves, and determining the normalized preferred curves.
In an embodiment of the present invention, when the apparatus for predicting a shear wave velocity provided by the embodiment of the present invention is implemented, the apparatus is further configured to determine a normalized preferred curve according to the following manner:
wherein x' is a normalized preferred curve; x is a preferred curve; μ is the mean of the preferred curves; σ is the variance of the preferred curve.
In an embodiment of the present invention, when the prediction apparatus of shear wave velocity is implemented specifically, the shear wave velocity prediction model determining module is specifically configured to:
establishing a depth feedforward neural network model by combining a conventional logging curve, dividing known well transverse wave speeds into a training set and a testing set, optimizing an activation function, and selecting the activation function with smaller training errors and testing errors;
selecting a learning rate by adopting a dichotomy method, and determining a global optimal value of the deep feedforward neural network model;
randomly initializing a weight matrix, training a deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of a training set and a testing set;
when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again;
when the error between the training set and the testing set reaches a set value, the model is stored;
and (4) connecting the stored models in parallel, averaging, and determining a transverse wave velocity prediction model.
In a specific implementation of the apparatus for predicting a shear wave velocity according to an embodiment of the present invention, in an embodiment, the module for determining a shear wave velocity prediction model is further configured to:
selecting a first learning rate to train the deep feedforward neural network model, and observing a training error of the first learning rate; meanwhile, a second learning rate is selected to train the deep feedforward neural network model, and a training error of the second learning rate is observed; wherein the first learning rate is greater than the second learning rate
Taking the midpoint of the first learning rate and the second learning rate as a midpoint learning rate, training the deep feedforward neural network model, and determining a midpoint learning rate training error;
judging whether the deep feedforward neural network model converges or not according to the training error of the first learning rate, the training error of the second learning rate and the training error of the midpoint learning rate;
and if the deep feedforward neural network model is not converged, the midpoint is taken from the midpoint learning rate to the direction of the second learning rate again until the deep feedforward neural network model is converged, and the global optimum value of the deep feedforward neural network model is determined.
To sum up, the method and apparatus for predicting shear wave velocity provided by the embodiments of the present invention optimize a conventional well logging curve based on a known well shear wave velocity curve, determine an optimized curve, perform normalization processing, establish a deep feedforward neural network model based on the optimized curve in combination with the conventional well logging curve, train with the known well shear wave velocity, determine a shear wave velocity prediction model, and finally input the optimized curve after normalization into the shear wave velocity prediction model to determine the shear wave velocity; in the whole prediction process of the transverse wave velocity, only a known well transverse wave velocity curve and a conventional logging curve of a pre-logging well are needed, the transverse wave velocity is accurately predicted directly from data, adjusting parameters are few, requirements for personnel are low, and the method can be widely applied to actual production. According to the method, on the basis of the transverse wave velocity of a known well, a correlation algorithm in deep learning and machine learning is introduced, known data are split into a training set and a testing set, an error curve in the testing set is monitored in the training process, a reliable model is obtained, and the models obtained through multiple times of learning are connected in parallel to obtain a final high-precision transverse wave velocity prediction model. The method starts from data directly, has few adjusting parameters and low requirements on personnel, and can be widely applied in actual production.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (14)
1. A method for predicting shear wave velocity, comprising:
acquiring a conventional logging curve and a known well transverse wave velocity curve;
determining a preferred curve according to a conventional logging curve and a known transverse wave velocity curve;
carrying out normalization processing on the optimized curve, and determining the optimized curve after normalization;
establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well shear wave speed, and determining a shear wave speed prediction model;
and inputting the normalized optimal curve into a transverse wave velocity prediction model to determine the transverse wave velocity.
2. The method of claim 1, wherein determining a preferred profile from the conventional log profile and the known well shear velocity profile comprises:
and according to a vector correlation calculation method, calculating a correlation coefficient between the conventional logging curve and the known well transverse wave velocity curve, and performing correlation coefficient matrix evaluation on the conventional logging curve according to the correlation coefficient to determine a preferred curve.
3. The method of claim 1, wherein normalizing the preferred curve to determine a normalized preferred curve comprises:
fitting the statistical distribution characteristics of the optimal curve by adopting a Gaussian distribution function, and determining the mean value and the variance of the optimal curve;
and carrying out normalization processing on the preferred curves according to the mean value and the variance of the preferred curves, and determining the normalized preferred curves.
4. A method according to claim 3, characterized in that the normalized preferred curve is determined as follows:
wherein x' is a normalized preferred curve; x is a preferred curve; μ is the mean of the preferred curves; σ is the variance of the preferred curve.
5. The method of claim 1, wherein building a deep feed-forward neural network model in conjunction with a conventional well log, trained with known well shear velocities, to determine a shear velocity prediction model, comprises:
establishing a depth feedforward neural network model by combining a conventional logging curve, dividing known well transverse wave speeds into a training set and a testing set, optimizing an activation function, and selecting the activation function with smaller training errors and testing errors;
selecting a learning rate by adopting a dichotomy method, and determining a global optimal value of the deep feedforward neural network model;
randomly initializing a weight matrix, inputting a training set and a test set into a deep feedforward neural network model, training the deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of the training set and the test set;
when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again;
when the error between the training set and the testing set reaches a set value, the model is stored;
and (4) connecting the stored models in parallel, averaging, and determining a transverse wave velocity prediction model.
6. The method of claim 5, wherein the selecting of the learning rate using dichotomy to determine the global optimum of the deep feedforward neural network model comprises:
selecting a first learning rate to train the deep feedforward neural network model, and observing a training error of the first learning rate; meanwhile, a second learning rate is selected to train the deep feedforward neural network model, and a training error of the second learning rate is observed; wherein the first learning rate is greater than the second learning rate;
taking the midpoint of the first learning rate and the second learning rate as a midpoint learning rate, training the deep feedforward neural network model, and determining a midpoint learning rate training error;
judging whether the deep feedforward neural network model converges or not according to the training error of the first learning rate, the training error of the second learning rate and the training error of the midpoint learning rate;
and if the deep feedforward neural network model is not converged, the midpoint is taken from the midpoint learning rate to the direction of the second learning rate again until the deep feedforward neural network model is converged, and the global optimum value of the deep feedforward neural network model is determined.
7. A device for predicting a shear wave velocity, comprising:
the data acquisition module is used for acquiring a conventional logging curve and a known well transverse wave velocity curve;
the optimal curve determining module is used for determining an optimal curve according to the conventional logging curve and the known well transverse wave velocity curve;
the normalization module is used for performing normalization processing on the optimized curve and determining the optimized curve after normalization;
the transverse wave velocity prediction model determining module is used for establishing a depth feedforward neural network model by combining a conventional logging curve, training by utilizing the known well transverse wave velocity and determining a transverse wave velocity prediction model;
and the transverse wave velocity determining module is used for inputting the normalized optimal curve into the transverse wave velocity prediction model to determine the transverse wave velocity.
8. The apparatus of claim 7, wherein the preference curve determining module is specifically configured to:
and according to a vector correlation calculation method, calculating a correlation coefficient between the conventional logging curve and the known well transverse wave velocity curve, and performing correlation coefficient matrix evaluation on the conventional logging curve according to the correlation coefficient to determine a preferred curve.
9. The apparatus of claim 7, wherein the normalization module is specifically configured to:
fitting the statistical distribution characteristics of the optimal curve by adopting a Gaussian distribution function, and determining the mean value and the variance of the optimal curve;
and carrying out normalization processing on the preferred curves according to the mean value and the variance of the preferred curves, and determining the normalized preferred curves.
10. The apparatus of claim 9, wherein the normalization module is further configured to determine the normalized preferred curve as follows:
wherein x' is a normalized preferred curve; x is a preferred curve; μ is the mean of the preferred curves; σ is the variance of the preferred curve.
11. The apparatus of claim 7, wherein the shear wave velocity prediction model determination module is specifically configured to:
establishing a depth feedforward neural network model by combining a conventional logging curve, dividing known well transverse wave speeds into a training set and a testing set, optimizing an activation function, and selecting the activation function with smaller training errors and testing errors;
selecting a learning rate by adopting a dichotomy method, and determining a global optimal value of the deep feedforward neural network model;
randomly initializing a weight matrix, inputting a training set and a test set into a deep feedforward neural network model, training the deep feedforward neural network model according to an activation function and a global optimum value, and monitoring errors of the training set and the test set;
when the error between the training set and the test set does not reach a set value, the weight matrix is initialized randomly again;
when the error between the training set and the testing set reaches a set value, the model is stored;
and (4) connecting the stored models in parallel, averaging, and determining a transverse wave velocity prediction model.
12. The apparatus of claim 11, wherein the shear wave velocity prediction model determination module is further configured to:
selecting a first learning rate to train the deep feedforward neural network model, and observing a training error of the first learning rate; meanwhile, a second learning rate is selected to train the deep feedforward neural network model, and a training error of the second learning rate is observed;
taking the midpoint of the first learning rate and the second learning rate as a midpoint learning rate, training the deep feedforward neural network model, and determining a midpoint learning rate training error;
judging whether the deep feedforward neural network model converges or not according to the training error of the first learning rate, the training error of the second learning rate and the training error of the midpoint learning rate;
and if the deep feedforward neural network model is not converged, the midpoint is taken from the midpoint learning rate to the direction of the second learning rate again until the deep feedforward neural network model is converged, and the global optimum value of the deep feedforward neural network model is determined.
13. A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the method of predicting shear wave velocity according to any one of claims 1 to 6.
14. A computer-readable storage medium storing a computer program for executing a method of predicting a shear wave velocity according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010434118.0A CN111751878B (en) | 2020-05-21 | 2020-05-21 | Method and device for predicting transverse wave speed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010434118.0A CN111751878B (en) | 2020-05-21 | 2020-05-21 | Method and device for predicting transverse wave speed |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111751878A true CN111751878A (en) | 2020-10-09 |
| CN111751878B CN111751878B (en) | 2023-05-30 |
Family
ID=72673433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010434118.0A Active CN111751878B (en) | 2020-05-21 | 2020-05-21 | Method and device for predicting transverse wave speed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111751878B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113466962A (en) * | 2021-07-06 | 2021-10-01 | 西安交通大学 | Transverse wave prediction method and system based on Gaussian process regression |
| WO2024040801A1 (en) * | 2022-08-26 | 2024-02-29 | 中国石油天然气股份有限公司 | Transverse wave time difference prediction method and apparatus |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107526117A (en) * | 2017-07-06 | 2017-12-29 | 天津科技大学 | SVEL Forecasting Methodology based on autocoding and the study joint network that transfinites |
| CN107678059A (en) * | 2017-09-05 | 2018-02-09 | 中国石油大学(北京) | A kind of method, apparatus and system of reservoir gas-bearing identification |
| WO2018201114A1 (en) * | 2017-04-28 | 2018-11-01 | Pioneer Natural Resources Usa, Inc. | High resolution seismic data derived from pre-stack inversion and machine learning |
| WO2019062655A1 (en) * | 2017-09-27 | 2019-04-04 | 中国石油天然气股份有限公司 | Method and device for determining thin interlayer |
| CN110703330A (en) * | 2018-07-10 | 2020-01-17 | 中国石油化工股份有限公司 | Carbonate rock logging correction and transverse wave velocity prediction method based on rock physics |
| US20200065620A1 (en) * | 2018-08-24 | 2020-02-27 | Petrochina Company Limited | Method and apparatus for automatically recognizing electrical imaging well logging facies |
| US20200088897A1 (en) * | 2018-09-14 | 2020-03-19 | Bp Corporation North America Inc. | Machine Learning-Based Analysis of Seismic Attributes |
| CN111144001A (en) * | 2019-12-26 | 2020-05-12 | 湖南科技大学 | Mine shaft engineering TBM control method based on BP neural network |
-
2020
- 2020-05-21 CN CN202010434118.0A patent/CN111751878B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018201114A1 (en) * | 2017-04-28 | 2018-11-01 | Pioneer Natural Resources Usa, Inc. | High resolution seismic data derived from pre-stack inversion and machine learning |
| CN107526117A (en) * | 2017-07-06 | 2017-12-29 | 天津科技大学 | SVEL Forecasting Methodology based on autocoding and the study joint network that transfinites |
| CN107678059A (en) * | 2017-09-05 | 2018-02-09 | 中国石油大学(北京) | A kind of method, apparatus and system of reservoir gas-bearing identification |
| WO2019062655A1 (en) * | 2017-09-27 | 2019-04-04 | 中国石油天然气股份有限公司 | Method and device for determining thin interlayer |
| CN110703330A (en) * | 2018-07-10 | 2020-01-17 | 中国石油化工股份有限公司 | Carbonate rock logging correction and transverse wave velocity prediction method based on rock physics |
| US20200065620A1 (en) * | 2018-08-24 | 2020-02-27 | Petrochina Company Limited | Method and apparatus for automatically recognizing electrical imaging well logging facies |
| US20200088897A1 (en) * | 2018-09-14 | 2020-03-19 | Bp Corporation North America Inc. | Machine Learning-Based Analysis of Seismic Attributes |
| CN111144001A (en) * | 2019-12-26 | 2020-05-12 | 湖南科技大学 | Mine shaft engineering TBM control method based on BP neural network |
Non-Patent Citations (1)
| Title |
|---|
| 王晓光等: "自适应BP神经网络在横波速度预测中的应用", 《岩性油气藏》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113466962A (en) * | 2021-07-06 | 2021-10-01 | 西安交通大学 | Transverse wave prediction method and system based on Gaussian process regression |
| WO2024040801A1 (en) * | 2022-08-26 | 2024-02-29 | 中国石油天然气股份有限公司 | Transverse wave time difference prediction method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111751878B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1984860B1 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| US8504341B2 (en) | Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| CN113553780B (en) | Stratum pore pressure prediction method based on machine learning | |
| CN110006568B (en) | Method and system for acquiring three-dimensional ground stress by using rock core | |
| CN110807557A (en) | Drilling rate prediction method based on BP neural network and drilling rate optimization method based on BP neural network and particle swarm optimization | |
| CN104533400A (en) | Method for reconstructing logging curve | |
| CN111751878B (en) | Method and device for predicting transverse wave speed | |
| CN114912364B (en) | Natural gas well flow prediction method, device, equipment and computer readable medium | |
| CN112253087A (en) | Biological disturbance reservoir physical property calculation method based on multi-source logging data | |
| CN115481565A (en) | Earth pressure balance shield tunneling parameter prediction method based on LSTM and ant colony algorithm | |
| CN114066084B (en) | Method and system for predicting phase permeation curve based on machine learning | |
| CN110988997A (en) | Hydrocarbon source rock three-dimensional space distribution quantitative prediction technology based on machine learning | |
| CN114488311A (en) | Transverse wave time difference prediction method based on SSA-ELM algorithm | |
| US20220245300A1 (en) | Method and system for constructing statistical emulators for reservoir simulation models with uncertain inputs | |
| CN111273349A (en) | Transverse wave velocity extraction method and processing terminal for seabed shallow sediment layer | |
| CN110414085A (en) | It has developed fault block oil reservoir original oil-water level and has determined method | |
| CN110486009A (en) | A kind of automatic reverse method of parameter and system on infinity stratum | |
| CN115049173A (en) | Deep learning and Eaton method coupling driving stratum pore pressure prediction method | |
| CN110032777B (en) | Drilling fluid density safety window estimation method based on uncertainty analysis | |
| CN114547958A (en) | Well-to-seismic combination fracture prediction method and device based on deep neural network | |
| CN111749675A (en) | Stratum drillability prediction method and system based on cascade model algorithm | |
| CN112946754B (en) | Reservoir porosity prediction method and device | |
| CN108875109B (en) | Method and system for predicting abnormal formation pressure | |
| CN116227335A (en) | Three-dimensional ground stress prediction method of parallel neural network based on physical constraint | |
| CN116068650A (en) | Transverse wave speed prediction method based on deep learning |
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 |