Fracture recognition in ultrasonic logging images via unsupervised segmentation network

Zhang, Wei; Wu, Tong; Li, Zhipeng; Liu, Shiyuan; Qiu, Ao; Li, Yanjun; Shi, Yibing

doi:10.1007/s12145-021-00605-6

Cited by 17 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The imaging logging identifying fractures is mainly based on the difference between the electrical resistivity of the fractured formation and that of the surrounding rock. In the formation with fractures, thanks to mud intrusion, the electrical resistivity of the fracture is significantly lower than that of the surrounding rock, which is shown as dark stripes on the imaging map. ,,− Different causes and different types of fractures have different image characteristics (Figure a). Therefore, imaging logging can be employed to identify fracture types, precisely calculate fracture occurrence, and analyze the development degree of the fractures.…”

Section: Samples and Methodsmentioning

confidence: 99%

Characteristics of Natural Fractures in an Ultradeep Marine Carbonate Gas Reservoir and Their Impact on the Reservoir: A Case Study of the Maokou Formation of the JLS Structure in the Sichuan Basin, China

Wang

Qin

et al. 2021

Energy Fuels

View full text Add to dashboard Cite

The primary gas layer of the Maokou Formation of the JLS structure in the Sichuan Basin is a typical pore-fracture carbonate gas reservoir. Natural fractures (mainly tectonic fractures) serve as the critical factor in improving the reservoir's physical properties. The characteristics, formation mechanisms of natural fractures, and their impact on the reservoir are analyzed using the core, thin slice, full microresistivity imager imaging logging, production testing, and the Monte Carlo method multiple approximations. The results show that the fractures in the Maokou Formation reservoir generally refer to shear fractures of a tectonic origin, with the characteristics of a medium scale (10−20 cm), a large inclination angle (45− 90), a high density (greater than 5 m −1 ), a medium opening (1−3 mm), and a low filling degree. There are three primary formation stages of natural fractures in the area, the Indosinian stage (232−210 Ma), the early-middle Yanshanian stage (145−90 Ma), and the late Yanshanian−Himalayan stage (90−0 Ma). The corresponding principal stress directions are NW, near-SN, and NNW, respectively. Natural fractures have a positive effect on the improvement of reservoir physical properties. The fracture's physical parameters show a good positive correlation with the physical properties of the reservoirs. The fracture parameters influence the reservoir's physical properties ranked from biggest to smallest: opening, length, and density. The greater the development degree of fractures, the greater the corresponding natural gas production capacity. The research results provide a new technical method for quantifying the influence of fracture parameters on reservoir's physical properties.

show abstract

Section: Samples and Methodsmentioning

confidence: 99%

Characteristics of Natural Fractures in an Ultradeep Marine Carbonate Gas Reservoir and Their Impact on the Reservoir: A Case Study of the Maokou Formation of the JLS Structure in the Sichuan Basin, China

Wang

Qin

et al. 2021

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Wang and Zhou used a W-shape dual encoder-decoder structure model to extract fractures in logging images [18]. Zhang et al used an unsupervised segmentation network to recognize fractures in ultrasonic logging images [19]. Although the ultrasonic imaging logging method can better respond to the fracture information under the extreme well conditions such as unconventional oil and gas resources, deep drilling, etc, it cannot meet the real-time requirements of fracture recognition and its fine description in the process of drilling [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Wellbore fracture recognition and fracture parameter identification method using piezoelectric ultrasonic and machine learning

Liu,

Luo,

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Real-time monitoring of wellbore status information can effectively ensure the structural safety of the wellbore and improve the drilling efficiency. It is especially important to recognize the wellbore fractures and identify their parameters, which motivates us to propose a wellbore fracture recognition and parameter identification method using piezoelectric ultrasonic and machine learning. To realize a Self-model Emission Detection (SED), we innovatively utilize a single transducer to act as both an actuator and a sensor, allowing for the efficient acquisition of ultrasonic echo signals of the wellbore. For fracture recognition, we use the wavelet packet transform to extract features from the ultrasonic echo signal, while constructing a Convolutional Neural Network (CNN) model for fracture recognition. Then, we establish the relationships between the fracture width-depth parameter and the echo signal, including the peak value as well as the arrival time difference. The experimental results show that the proposed method effectively recognizes the fractures from the ultrasonic echo signal of the wellbore. At the same time, the established function truly reflects the relationship between the fracture parameters and the echo signal. Therefore, the proposed method can provide an identification function for quantitative monitoring of wellbore fracture parameters. Moreover, the functions can be used as a reference for other structural health monitoring, which has good application prospects.

show abstract

“…As an alternative approach, various supervised (Karimpouli et al 2020;Lu et al 2020;Lee et al 2021) and unsupervised (Taibi et al 2019;Zhang et al 2021) machine learning techniques were implemented for fracture identification and segmenting porous samples (Chauhan et al 2016). Among the unsupervised approaches, encoder-decoder networks in the form of CNNs received much attention during fracture identification in the DRP workflow (Varfolomeev et al 2019;Hong & Liu 2020;Karimpouli et al 2020;Kim et al 2020;Lu et al 2020;Lee et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks

et al. 2022

View full text Add to dashboard Cite

Image segmentation remains the most critical step in Digital Rock Physics (DRP) workflows, affecting the analysis of physical rock properties. Conventional segmentation techniques struggle with numerous image artifacts and user bias, which lead to considerable uncertainty. This study evaluates the advantages of using the random forest (RF) algorithm for the segmentation of fractured rocks. The segmentation quality is discussed and compared with two conventional image processing methods (thresholding-based and watershed algorithm) and an encoder–decoder network in the form of convolutional neural networks (CNNs). The segmented images of the RF method were used as the ground truth for CNN training. The images of two fractured rock samples are acquired by X-ray computed tomography scanning (XCT). The skeletonized 3D images are calculated, providing information about the mean mechanical aperture and roughness. The porosity, permeability, flow fields, and preferred flow paths of segmented images are analyzed by the DRP approach. Moreover, the breakthrough curves obtained from tracer injection experiments are used as ground truth to evaluate the segmentation quality of each method. The results show that the conventional methods overestimate the fracture aperture. Both machine learning approaches show promising segmentation results and handle all artifacts and complexities without any prior CT-image filtering. However, the RF implementation has superior inherent advantages over CNN. This method is resource-saving (e.g., quickly trained), does not need an extensive training dataset, and can provide the segmentation uncertainty as a measure for evaluating the segmentation quality. The considerable variation in computed rock properties highlights the importance of choosing an appropriate segmentation method.

show abstract

Fracture recognition in ultrasonic logging images via unsupervised segmentation network

Cited by 17 publications

References 17 publications

Characteristics of Natural Fractures in an Ultradeep Marine Carbonate Gas Reservoir and Their Impact on the Reservoir: A Case Study of the Maokou Formation of the JLS Structure in the Sichuan Basin, China

Characteristics of Natural Fractures in an Ultradeep Marine Carbonate Gas Reservoir and Their Impact on the Reservoir: A Case Study of the Maokou Formation of the JLS Structure in the Sichuan Basin, China

Wellbore fracture recognition and fracture parameter identification method using piezoelectric ultrasonic and machine learning

Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks

Contact Info

Product

Resources

About