CN-122024886-A - Shale reservoir analysis method and device, electronic equipment and storage medium

CN122024886ACN 122024886 ACN122024886 ACN 122024886ACN-122024886-A

Abstract

The invention provides a shale reservoir analysis method, a shale reservoir analysis device, electronic equipment and a shale reservoir storage medium, wherein the shale reservoir analysis method comprises the steps of obtaining a first longitudinal wave speed, a first transverse wave speed, a first density and a first porosity of a shale reservoir through seismic prestack inversion research; the method comprises the steps of calculating a first elastic modulus parameter based on a shale reservoir physical model, determining a stiffness coefficient matrix according to a first longitudinal wave speed, a first transverse wave speed, a first density, a first porosity and the first elastic modulus parameter of the shale reservoir, determining a first sensitive parameter according to coefficients contained in the stiffness coefficient matrix, determining a second sensitive parameter according to an output value obtained by inversion of the shale reservoir physical model, inputting the first longitudinal wave speed, the second transverse wave speed and the first density into a first deep learning model, determining a third sensitive parameter, and inputting the first sensitive coefficient, the second sensitive coefficient and the third sensitive coefficient into a second deep learning model to determine a target brittleness index of the shale reservoir.

Inventors

LIU DI
YANG PING
GAO YINGNAN
XU CHEN
JU PENG
HUANG YAN

Assignees

中国石油天然气集团有限公司
中国石油集团东方地球物理勘探有限责任公司
中油油气勘探软件国家工程研究中心有限公司

Dates

Publication Date: 20260512
Application Date: 20241112

Claims (10)

1. A method of shale reservoir analysis, for application to an electronic device, the method comprising: obtaining a first longitudinal wave speed, a first transverse wave speed, a first density and a first porosity of a shale reservoir through seismic prestack inversion research; Calculating a first elastic modulus parameter of the shale reservoir based on a pre-constructed shale reservoir physical model, wherein the first elastic modulus parameter comprises bulk modulus, shear modulus and second density; determining a stiffness coefficient matrix of the shale reservoir according to a first longitudinal wave speed, a first transverse wave speed, a first density, a first porosity and a first elastic modulus parameter of the shale reservoir; determining a first sensitivity parameter according to coefficients contained in a stiffness coefficient matrix of the shale reservoir; Determining a second sensitive parameter according to an output value obtained by inversion of the shale reservoir physical model; inputting the first longitudinal wave speed, the second transverse wave speed and the first density of the shale reservoir into a pre-trained first deep learning model, and determining a third sensitive parameter; and inputting the first sensitivity coefficient, the second sensitivity coefficient and the third sensitivity coefficient into a pre-trained second deep learning model, and determining the target brittleness index of the shale reservoir.
2. The method of claim 1, wherein determining the first sensitivity parameter from coefficients contained in a matrix of stiffness coefficients of the shale reservoir comprises: Calculating the product of a first coefficient and a second coefficient in the rigidity coefficient matrix; determining a ratio of the product to a third coefficient as a first sensitivity parameter; the first coefficient is used for representing longitudinal wave rigidity in the direction perpendicular to the axis of the well bore, the second coefficient is used for representing transverse wave rigidity, and the third coefficient is used for representing shear rigidity in the direction parallel to the surface of the shale reservoir layer.
3. The method of claim 1, wherein the determining the second sensitivity parameter from the output values obtained by inversion of the shale reservoir physical model comprises: Inverting the shale reservoir physical model, and determining that the contents of the current brittle mineral components and the non-brittle mineral components are target contents of the brittle mineral components and the non-brittle mineral components in the shale reservoir under the condition that the output value of the shale reservoir physical model meets the preset condition; determining the second sensitive parameter according to the target content of the brittle mineral component and the non-brittle mineral component.
4. The method of claim 1, wherein the inputting the first longitudinal wave velocity, the second transverse wave velocity, the first density of the shale reservoir into the pre-trained first deep learning model, determining the third sensitivity parameter comprises: Calculating a first brittleness index of the shale reservoir according to the measured contents of brittle minerals and non-brittle minerals in the shale reservoir; Constructing a training sample set according to the actual measured longitudinal wave speed, the actual measured transverse wave speed, the actual measured density and the first brittleness index of the shale reservoir, wherein a training sample in the training sample set comprises an array formed by the actual measured longitudinal wave speed, the actual measured transverse wave speed and the actual measured density, and the first brittleness index is a reference result corresponding to the array; Training the first deep learning model based on the training sample set; And inputting the first longitudinal wave speed, the second transverse wave speed and the second density of the shale reservoir into a trained second deep learning model, and determining a third sensitive parameter.
5. The method of claim 1, wherein determining a stiffness coefficient matrix for the shale reservoir based on a first longitudinal wave velocity, a first shear wave velocity, a first density, a first porosity, and a first elastic modulus parameter of the shale reservoir comprises: Inputting the first longitudinal wave speed, the first transverse wave speed, the first density, the first porosity and the first elastic modulus parameters of the shale reservoir into a pre-trained third deep learning model, and predicting the rigidity coefficient matrix of the shale reservoir through the third deep learning model.
6. The method of claim 1, wherein obtaining a first longitudinal wave velocity, a first shear wave velocity, a first density, a first porosity of the shale reservoir via a seismic prestack inversion study comprises: acquiring a first longitudinal wave speed, a first transverse wave speed and a first wave impedance of the shale reservoir through seismic prestack inversion research; Determining first porosities corresponding to the first wave impedance and the second parameter according to a fitting relation among the measured wave impedance, the first parameter and the measured porosity of the shale reservoir; The first parameter is the ratio of the measured longitudinal wave speed to the transverse wave speed of the shale reservoir, and the second parameter is the ratio of the first longitudinal wave speed to the first transverse wave speed.
7. The method of claim 1, wherein the calculating a first elastic modulus parameter of the shale reservoir based on a pre-constructed shale reservoir physical model comprises: Calculating third elastic modulus parameters of at least two target positions based on the shale reservoir physical model; Fitting the third elastic modulus parameter, and determining the first elastic modulus parameter.
8. An apparatus for analysis of a shale reservoir, the apparatus comprising: The inversion module is used for obtaining a first longitudinal wave speed, a first transverse wave speed, a first density and a first porosity of the shale reservoir through seismic prestack inversion research; The calculation module is used for calculating a first elastic modulus parameter of the shale reservoir based on a pre-constructed shale reservoir physical model, wherein the first elastic modulus parameter comprises bulk modulus, shear modulus and second density; the first determining module is used for determining a rigidity coefficient matrix of the shale reservoir according to a first longitudinal wave speed, a first transverse wave speed, a first density, a first porosity and a first elasticity modulus parameter of the shale reservoir; The second determining module is used for determining a first sensitive parameter according to coefficients contained in the rigidity coefficient matrix of the shale reservoir; The third determining module is used for determining a second sensitive parameter according to an output value obtained by inversion of the shale reservoir physical model; a fourth determining module, configured to input a first longitudinal wave velocity, a second transverse wave velocity, and a first density of the shale reservoir into a first deep learning model trained in advance, and determine a third sensitivity parameter; and a fifth determining module, configured to input the first sensitivity coefficient, the second sensitivity coefficient and the third sensitivity coefficient into a pre-trained second deep learning model, and determine a target brittleness index of the shale reservoir.
9. An electronic device, comprising a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface are in communication with each other via the communication bus, and wherein the memory is configured to store executable instructions that cause the processor to perform the shale reservoir analysis method of any of claims 1-6.
10. A readable storage medium having stored thereon a program or instructions which when executed by a processor performs the method of analysis of shale reservoirs of any of claims 1 to 6.

Description

Shale reservoir analysis method and device, electronic equipment and storage medium Technical Field The invention relates to the field of oil-gas seismic exploration and development, in particular to a shale reservoir analysis method, a shale reservoir analysis device, electronic equipment and a shale reservoir storage medium. Background In recent years, as the recoverable reserves of oil and gas in conventional reservoirs gradually decrease, unconventional reservoirs represented by shale reservoirs are receiving more and more attention. Shale reservoirs have typical ultra-low hole and ultra-low permeability characteristics, when shale oil gas development is carried out, fracturing is required, and due to the fact that the cost of fracturing construction of the shale reservoirs is huge, the fracturing effect is required to be estimated before the fracturing construction, and the brittleness index of the shale reservoirs is an important factor affecting the fracturing effect of the shale reservoirs. The existing method for calculating the brittleness index needs to be carried out in a laboratory based on analysis of hardness and strength, and is difficult to apply to three-dimensional earthquake. Some scholars propose to use the modulus of elasticity to describe brittle characteristics. For example, rickman et al propose to use normalized young's modulus and poisson's ratio to calculate the brittleness index, but calculating brittleness using this method does not coincide with many of the tight reservoirs in our country, and it is difficult to interpret changes in lithology. Disclosure of Invention The invention provides a shale reservoir analysis method, a shale reservoir analysis device, electronic equipment and readable storage media, which can improve the accuracy of calculating the brittleness index of the shale reservoir. The method comprises the following steps: obtaining a first longitudinal wave speed, a first transverse wave speed, a first density and a first porosity of a shale reservoir through seismic prestack inversion research; Calculating a first elastic modulus parameter of the shale reservoir based on a pre-constructed shale reservoir physical model, wherein the first elastic modulus parameter comprises bulk modulus, shear modulus and second density; determining a stiffness coefficient matrix of the shale reservoir according to a first longitudinal wave speed, a first transverse wave speed, a first density, a first porosity and a first elastic modulus parameter of the shale reservoir; determining a first sensitivity parameter according to coefficients contained in a stiffness coefficient matrix of the shale reservoir; Determining a second sensitive parameter according to an output value obtained by inversion of the shale reservoir physical model; inputting the first longitudinal wave speed, the second transverse wave speed and the first density of the shale reservoir into a pre-trained first deep learning model, and determining a third sensitive parameter; and inputting the first sensitivity coefficient, the second sensitivity coefficient and the third sensitivity coefficient into a pre-trained second deep learning model, and determining the target brittleness index of the shale reservoir. Optionally, the determining a first sensitivity parameter according to coefficients contained in a stiffness coefficient matrix of the shale reservoir comprises: Calculating the product of a first coefficient and a second coefficient in the rigidity coefficient matrix; determining a ratio of the product to a third coefficient as a first sensitivity parameter; the first coefficient is used for representing longitudinal wave rigidity in the direction perpendicular to the axis of the well bore, the second coefficient is used for representing transverse wave rigidity, and the third coefficient is used for representing shear rigidity in the direction parallel to the surface of the shale reservoir layer. Optionally, the determining the second sensitive parameter by the output value obtained by inversion of the shale reservoir physical model includes: Inverting the shale reservoir physical model, and determining that the contents of the current brittle mineral components and the non-brittle mineral components are target contents of the brittle mineral components and the non-brittle mineral components in the shale reservoir under the condition that the output value of the shale reservoir physical model meets the preset condition; determining the second sensitive parameter according to the target content of the brittle mineral component and the non-brittle mineral component. Optionally, the inputting the first longitudinal wave velocity, the second transverse wave velocity, and the first density of the shale reservoir into a pre-trained first deep learning model, determining a third sensitivity parameter includes: Calculating a first brittleness index of the shale reservoir according to the measured contents of br