Method and system for constructing digital rock

Patent metadata

Field	Value
Publication number	US-11934488-B2
Application number	US-202017295493-A
Country	US
Kind code	B2
Filing date	Sep 10, 2020
Priority date	Mar 13, 2020
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

Abstract

The present disclosure provides a method and system for constructing a digital rock, and relates to the technical field of digital rocks. According to the method, a three-dimensional (3D) digital rock image that can reflect real rock information is obtained using an image scanning technology, and the image is preprocessed to obtain a digital rock training image for training a generative adversarial network (GAN). The trained GAN is stored to obtain a digital rock construction model. The stored digital rock construction model can be directly used to quickly construct a target digital rock image. This not only greatly reduces computational costs, but also reduces costs and time consumption for obtaining high-resolution sample images. In addition, the constructed target digital rock image can also reflect real rock information.

First claim

What is claimed is:

1. A method for constructing a digital rock, comprising:
obtaining a digital rock training image, wherein the digital rock training image is a digital rock sample image of a known rock;
extracting a plurality of sub-samples from the digital rock training image, and storing all the sub-samples as a sample set;
training a generative adversarial network (GAN) using the sample set and a random sample noise to obtain a digital rock construction model, wherein the digital rock construction model is the GAN trained using the sample set and the random sample noise, and the digital rock construction model is configured to construct a target digital rock image;
obtaining a target random noise; and
inputting the target random noise into the digital rock construction model to obtain the target digital rock image,
wherein obtaining a digital rock training image comprises:
scanning the known rock using an image scanning technology to obtain a grayscale image of the known rock;
extracting a representative elementary volume (REV) from the center of the grayscale image of the known rock, and smoothing the REV to obtain a smooth digital rock image; and
segmenting the smooth digital rock image using a watershed segmentation method to obtain the digital rock training image.

2. The method for constructing a digital rock according to claim 1 , wherein the training a GAN using the sample set and a random sample noise to obtain a digital rock construction model comprises:
obtaining an activation function and a loss function of the GAN, wherein the GAN comprises a generator network and a discriminator network;
inputting the random sample noise into the generator network to obtain a fake sample set, wherein the fake sample set comprises a plurality of first fake digital rock images;
training the discriminator network using the fake sample set and the sample set to obtain a discriminator network model, wherein the discriminator network model is the trained discriminator network, an input of the discriminator network model is the first fake digital rock image, and an output is a real or fake probability value of the first fake digital rock image; and
using the random sample noise as input, and training the generator network using the trained discriminator network model to obtain a generator network model, wherein the generator network model is the trained generator network, the output of the generator network model is the target digital rock image, and the discriminator network model and the generator network model constitute the digital rock construction model.

3. The method for constructing a digital rock according to claim 2 , wherein the discriminator network comprises a discriminator input layer, discriminator intermediate layers, and a discriminator output layer;
the generator network comprises a generator input layer, generator intermediate layers, and a generator output layer, wherein the generator input layer is a fully connected layer, and the generator intermediate layers and the generator output layer are both micro-step convolutional layers;
the activation function comprises an activation function of the discriminator intermediate layer, an activation function of the discriminator output layer, an activation function of the generator intermediate layer, and an activation function of the generator output layer; the activation function of the discriminator intermediate layer is a LeakyReLu activation function, the activation function of the discriminator output layer is a Sigmoid activation function, the activation function of the generator intermediate layer is a ReLu activation function, and the activation function of the generator output layer is a Tanh activation function, and
the loss function comprises a discriminator loss function of the discriminator network and a generator loss function of the generator network.

4. The method for constructing a digital rock according to claim 3 , wherein the training the discriminator network using the fake sample set and the sample set to obtain a discriminator network model comprises:
extracting N sub-samples from the sample set, and inputting the N sub-samples into the discriminator network to calculate a first discriminator loss function;
calculating a first discriminator gradient of each layer of the discriminator network using the first discriminator loss function;
extracting N first fake digital rock images from the fake sample set, and inputting the N first fake digital rock images into the discriminator network to calculate a second discriminator loss function;
calculating a second discriminator gradient of each layer of the discriminator network using the second discriminator loss function;
adding the first discriminator loss function and the second discriminator loss function to obtain the discriminator loss function; and
optimizing the discriminator loss function using the first discriminator gradient, the second discriminator gradient, and a mini-batch gradient descent algorithm to obtain optimal discriminator network parameters, and obtaining the discriminator network model based on the optimal discriminator network parameters, wherein the discriminator network parameters are a weight and bias of each layer of the discriminator network.

5. The method for constructing a digital rock according to claim 3 , wherein the using the random sample noise as input, and training the generator network using the trained discriminator network model to obtain a generator network model comprises:
inputting the random sample noise into the generator network to generate a first fake sample;
inputting the first fake sample into the discriminator network model, and calculating a first loss function according to formula Loss_S1=lg(D(G(z,θ)),α)) wherein Loss_S1 denotes the first loss function, D(⋅) denotes the discriminator network model, G(⋅) denotes the generator network, z denotes the random sample noise, a denotes the discriminator network parameter, and θ denotes a generator network parameter;
calculating a generator gradient of each layer of the generator network using the first loss function, and
optimizing the generator loss function using the generator gradient and the mini-batch gradient descent algorithm; going back to the step of “inputting the random sample noise into the generator network to generate a first fake sample” for iteration until a number of iterations reaches a predetermined value or a real or fake probability value of the discriminator network model is a predetermined real or fake probability value; when the number of iterations reaches the predetermined value or the real or fake probability value is the predetermined real or fake probability value, determining corresponding generator network parameters as optimal generator network parameters; and obtaining the generator network model based on the optimal generator network parameters, wherein the generator network parameters are a weight and bias of each layer of the generator network.

6. A system for constructing a digital rock, comprising:
a digital rock training image module, configured to obtain a digital rock training image, wherein the digital rock training image is a digital rock sample image of a known rock,
a sample set module, configured to extract a plurality of sub-samples from the digital rock training image, and store all the sub-samples as a sample set;
a digital rock model module, configured to train a generative adversarial network (GAN) using the sample set and a random sample noise to obtain a digital rock construction model, wherein the digital rock construction model is the GAN trained using the sample set and the random sample noise, and the digital rock construction model is configured to construct a target digital rock image;
an ob

Assignees

• Univ China Petroleum East China

Inventors

• Yang Yongfei
• Liu Fugui
• Yao Jun
• Song Huaisen
• Zhang Kai
• Zhang Lei
• Sun Hai
• Song Wenhui
• Wang Yuanbo
• Xu Bozhao

Classifications

• G06N3/0475

  Generative networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/094

  Adversarial learning · CPC title

• G06F18/2148 Primary

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06N3/045

  Combinations of networks · CPC title