Deep convolutional neural network for fast determination of the rock strength parameters using drilling data

He, Mingming; Zhang, Zhiqiang; Ren, Jie; Huan, Jiuyang; Li, Guofeng; Chen, Yunsheng; Li, Ning

doi:10.1016/j.ijrmms.2019.104084

Cited by 84 publications

(27 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…So, the deformation modulus is as one of the soil parameters. e parameters required for the numerical simulation were based on the relevant literature [30][31][32][33][34][35], as shown in Table 2. e corresponding structures of tunnel and utility tunnel are simplified as elastic models.…”

Section: Materials Model and Parametersmentioning

confidence: 99%

Influence of Utility Tunnel on the Lower Part of the Existing Double‐Track Shield Tunnel in Loess Soil

Yang

et al. 2021

Advances in Materials Science and Engineering

Self Cite

View full text Add to dashboard Cite

The interaction between the double-track shield tunnel and the integrated pipe gallery is complex, and there is still a lack of systematic research. Based on the numerical simulation of the Xi’an case, this paper studies the influence of the construction of the integrated pipe gallery on the deformation characteristics of the existing double-line subway tunnels with different buried depths and clear distances and finds the safe buried depth and clear distance of the tunnel. The results indicated that, in the loess area, the maximum deformation of the existing subway has a linear and inverse relationship with the buried depth and spacing, respectively. Increasing the buried depth can reduce the impact of the upper construction disturbance more than increasing the clear distance ratio. Moreove, under the design conditions of constructing a utility tunnel by the open-cut method, when the buried depth of the tunnel is 4.5 D and the spacing is greater than 4.5 D, or the buried depth is 5.0 D and the spacing is greater than 2.5 D, the combination of subway tunnels can meet the deformation control standards.

show abstract

Section: Materials Model and Parametersmentioning

confidence: 99%

Influence of Utility Tunnel on the Lower Part of the Existing Double‐Track Shield Tunnel in Loess Soil

Yang

et al. 2021

Advances in Materials Science and Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Geotechnical engineering problems in civil, mining, and petroleum engineering practices [1]: the mechanical properties of rock have become the most common measurement in most rock mass classification systems [2,3]. In the field of underground engineering, rocks undergo the complex energy change, which includes energy input, accumulation, dissipation, and release [4,5].…”

Section: Introductionmentioning

confidence: 99%

Energy Dissipation-Based Method for Strength Determination of Rock under Uniaxial Compression

Pang

Wang

et al. 2020

Shock and Vibration

View full text Add to dashboard Cite

The energy conversion in rocks has an important significance for evaluation of the stability and safety of rock engineering. In this paper, some uniaxial compression tests for fifteen different rocks were performed. The evolution characteristics of the total energy, elastic energy, and dissipated energy for the fifteen rocks were studied. The dissipation energy coefficient was introduced to study the evolution characteristics of rock. The evolution of the dissipation energy coefficient for different rocks was investigated. The linear interrelations of the dissipation energy coefficients and the yield strength and peak strength were explored. The method was proposed to determine the strength of rock using the dissipation energy coefficients. The results show that the evolution of the dissipation energy coefficient exhibits significant deformation properties of rock. The dissipation energy coefficients linearly increase with the compaction strength, but decrease with the yield strength and peak strength. Moreover, the dissipation energy coefficient can be used to determine the rock burst proneness and crack propagation in rocks.

show abstract

Section: Introductionmentioning

confidence: 99%

“…It has been shown in another recent study that deep convolutional neural networks could be effectively implemented and used for the determination of rock strength parameters [15]. They used the images of several types of rocks to train the CNN and to estimate the rock strength parameters where they obtained very high R 2 scores such as 0.998 [15]. It should also be mentioned that CNN can be adapted and used successfully for very difficult problems with complex image analysis such as quantifying image distortions caused by strong gravitational lenses [16].…”

Section: Introductionmentioning

confidence: 99%

A convolutional neural network model for marble quality classification

Karaali

Eminağaoğlu

2020

SN Appl. Sci.

View full text Add to dashboard Cite

The fundamental policy of marble industries is to establish sustainable high-quality products in a standardized manner. Identification and classification of different types of marbles is a critical task that is usually carried out by human experts. However, marble quality classification by humans can be time-consuming, error-prone, inconsistent, and subjective. Automated and computerized approaches are required to obtain faster, more reliable, and less subjective results. In this study, a deep learning model is developed to perform multi-classification of marble slab images with six different quality types. Blur filter, 5 ✕ 5 low-pass 2D linear separable convolution filter using Gaussian kernel, and erosion filter were applied to the images for data augmentation, and a special convolutional neural network (CNN) architecture was designed and implemented. It has been observed that the data augmentation approach for marble image samples has significantly improved the accuracy of the CNN model ranging between 0.922 and 0.961.

show abstract

Deep convolutional neural network for fast determination of the rock strength parameters using drilling data

Cited by 84 publications

References 45 publications

Influence of Utility Tunnel on the Lower Part of the Existing Double‐Track Shield Tunnel in Loess Soil

Influence of Utility Tunnel on the Lower Part of the Existing Double‐Track Shield Tunnel in Loess Soil

Energy Dissipation-Based Method for Strength Determination of Rock under Uniaxial Compression

A convolutional neural network model for marble quality classification

Contact Info

Product

Resources

About