A Multidimensional Clustering Analysis Method for Dividing Rock Mass Homogeneous Regions Based on the Shape Dissimilarity of Trace Maps

Wang, Jiongchao; Zheng, Jinhai; Lü, Qing; Guo, Jichao; He, Mingming; Deng, Jiang

doi:10.1007/s00603-020-02145-9

Cited by 10 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5. Usually, as few handled features as possible should be reserved, and the PI value should be higher than 0.95 30 . As Fig.…”

Section: Results Of Normalization and Dimension Reductionmentioning

confidence: 99%

K-means-based heterogeneous tunneling data analysis method for evaluating rock mass parameters along a TBM tunnel

Wang,

Zhang

2023

Sci Rep

View full text Add to dashboard Cite

Rapid and accurate judgment of the rock mass condition is the key to guaranteeing the safety and efficiency of tunnel boring machine (TBM) tunneling. This paper proposes a method for evaluating rock mass parameters based on K-means clustering, grouping tunneling areas according to the values of TBM tunneling parameters. A dataset including rock mass and TBM tunneling data is treated by logistic normalization and principal component analysis (PCA), and large volumes of tunneling data with different features are transformed into appropriate volumes of dimensionless data. K-means clustering is used, samples are grouped according to the values of tunneling data, and the specific ranges as defined by clustering are regarded as the unified evaluated results of each group. Based on the C1 part of the Pearl Delta water resources allocation project, 100 training samples and 30 testing samples were field-collected, and the proposed method was realized by the training samples and verified by the testing samples. The evaluation accuracies of uniaxial compressive strength (UCS), and joint frequency (Jf) were 90%, and 86.7% respectively, demonstrating that the evaluation had acceptable values, and the proposed method was greatly helpful for judging rock conditions.

show abstract

“…5. Usually, as few handled features as possible should be reserved, and the PI value should be higher than 0.95 30 . As Fig.…”

Section: Results Of Normalization and Dimension Reductionmentioning

confidence: 99%

K-means-based heterogeneous tunneling data analysis method for evaluating rock mass parameters along a TBM tunnel

Wang,

Zhang

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This comparison is mainly based on subjective judgment and statistical parameters obtained through a window survey and scanline (Xu & Dowd, 2010). In order to improve the consistency between the model and reality, some researchers have carried out studies on geometric assumptions (Guo et al., 2020), statistical distributions (Zheng et al., 2014), and statistical inferences (J. Wang et al., 2020). However, the results obtained rely on assuming statistical homogeneity in the rock mass.…”

Section: Literature Reviewmentioning

confidence: 99%

Rock mass fracture maps prediction based on spatiotemporal image sequence modeling

Xue

Cao

Zhou

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Discontinuities in rock mass are the characteristic challenge of rock tunnel engineering projects, which have a vital impact on rock mass exposures' mechanical and hydrological characteristics. There is a growing demand for predicting the fracture maps during tunnel excavation to ensure a smooth tunnel excavation process. The computer vision measurement of fractures in the tunnel surface is a current hot spot, but the traditional statistical analysis methods for fractures are still mainstream. This paper uses a novel perspective of the time‐space sequence to explain the continuously exposed rock mass during tunneling. A spatial‐aware recurrent neural network is proposed, which takes the historical fracture maps as the input to predict the unexcavated part. The experimental results suggest that the proposed model produces reliable performance and is superior to the other two state‐of‐the‐art deep learning models. Moreover, the test on the site rock tunnel data suggested promising results for fracture map predictions.

show abstract

“…Oil and gas exploration professionals are increasingly favoring unconventional and deep oil and gas reservoirs as a result of increased global efforts in this area. − Fractures, which are common in many different rock types and serve as the path for oil and gas reservoirs and migration, have an impact on the reservoir’s permeability and connectivity and directly affect how much oil and gas is produced. Fractures frequently result in complex fracture networks in subsurface rocks due to the combination of development and formation, rock mechanics, and fracturing. − Due to this, the creation of a plausible fracture network model to depict fractures has emerged as a crucial hot topic in the oil and gas sector as well as in geosciences. − …”

Section: Introductionmentioning

confidence: 99%

“… 1 − 7 Due to this, the creation of a plausible fracture network model to depict fractures has emerged as a crucial hot topic in the oil and gas sector as well as in geosciences. 8 − 11 …”

Section: Introductionmentioning

confidence: 99%

Natural Fracture Occurrence Model Based on FMI Imaging Logging

Wang

et al. 2023

ACS Omega

View full text Add to dashboard Cite

Natural fractures are crucial for connecting with reservoir matrix pores and influencing the fluid velocity in the matrix during unconventional oil and gas development. The development of natural fractures has significant impact on the effectiveness of extraction and even the final recovery factor. The development stage of natural fractures in reservoirs is characterized by fracture density and fracture occurrence, which are the key characteristics. The probabilistic models of fracture occurrence and density that are now available, however, still have several drawbacks. Therefore, a fracture occurrence model that may reflect both inclination and dip angles is proposed in a three-dimensional scenario in this study based on formation micro-imager imaging logging and the elliptic Fisher model. The findings demonstrate the accuracy and clarity of the proposed 3D fracture occurrence model in reflecting the fracture density and occurrence, as well as the superiority of data simulation. The algorithm described in this study is shown to be very close to the real distribution law. The results enable visualization of the fracture density and occurrence, which is crucial for directing engineering practice and assessing the sensitivity of directional data in other domains.

show abstract

A Multidimensional Clustering Analysis Method for Dividing Rock Mass Homogeneous Regions Based on the Shape Dissimilarity of Trace Maps

Cited by 10 publications

References 35 publications

K-means-based heterogeneous tunneling data analysis method for evaluating rock mass parameters along a TBM tunnel

K-means-based heterogeneous tunneling data analysis method for evaluating rock mass parameters along a TBM tunnel

Rock mass fracture maps prediction based on spatiotemporal image sequence modeling

Natural Fracture Occurrence Model Based on FMI Imaging Logging

Contact Info

Product

Resources

About