☆ 4.7 Article

Classifying Rock Fragments Produced by Tunnel Boring Machine Using Optimized Convolutional Neural Network

ROCK MECHANICS AND ROCK ENGINEERING (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Automation & Control Systems

Inspection of sandblasting defect in investment castings by deep convolutional neural network

Jenn-Kun Kuo et al.

Summary: This study successfully applied automated optical inspection (AOI) combined with convolutional neural networks (CNNs) to detect sandblasting defects in investment castings, reducing labor costs and improving employee health and safety. Among the four classic CNN models tested, AlexNet and VGG-16 showed the highest accuracy in defect detection, with a prediction accuracy of 100% for defective products.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Geological

Influence of Geological Properties and Operational Parameters on TBM Muck Removal Performance for Yinsong Tunnel

Yimin Xia et al.

Summary: This study investigated the operational parameters of a Tunnel Boring Machine (TBM) under different geological properties, established a muck model, studied the influence of advancement speed and rotational speed on muck removal performance through numerical simulations, and ultimately built an evaluation system for TBM muck removal performance to obtain optimal operation parameters. The accuracy of the simulation method was validated through on-site muck specimen analysis.

GEOTECHNICAL AND GEOLOGICAL ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Establish a patent risk prediction model for emerging technologies using deep learning and data augmentation

Yung-Chang Chi et al.

Summary: Technology patents are essential for emerging technologies, but obtaining them can be time-consuming, expensive, and risky. This research focuses on evaluating patent applications and identifying infringement risks using a prediction model based on Convolutional Neural Networks (CNN) and Long Short Term Memory Network (LSTM). The experimental results show that the model has an accuracy of at least 87.7% in predicting patent examination outcomes and identifying reasons for rejection.

ADVANCED ENGINEERING INFORMATICS (2022)

添加到收藏夹

Article Automation & Control Systems

A Convolutional Neural Network (CNN) classification to identify the presence of pores in powder bed fusion images

Muhammad Ayub Ansari et al.

Summary: This study uses convolutional neural networks to detect seeded porosity during metal additive manufacturing. The application of machine learning in in-process monitoring is demonstrated. Through synthetic defects and accurate labelling strategies, the efficacy of applying machine learning for defect detection in laser powder bed fusion is assessed. The proposed model achieves high accuracy and detection capability, leading to significant cost reduction in post-processing.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Civil

Predicting permeability from 3D rock images based on CNN with physical information

Pengfei Tang et al.

Summary: This paper proposes a new method based on convolutional neural networks and physical information for rapidly evaluating rock permeability. By utilizing reconstructed rock images and calculating corresponding permeability, the results show that this method achieves superior performance in small dataset and out-of-range problems.

JOURNAL OF HYDROLOGY (2022)

添加到收藏夹

Article Engineering, Geological

Automated Rock Quality Designation Using Convolutional Neural Networks

Fatimah Alzubaidi et al.

Summary: Mineral and hydrocarbon exploration heavily relies on geological and geotechnical information extracted from drill cores. Traditional drill-core characterization based on subjective expertise lacks generalization and robustness. This study proposes a computer vision and machine learning-based approach using convolutional neural networks to automatically classify and analyze drill core images for accurate estimation of the rock quality designation (RQD) parameter. Testing on sandstone and limestone core images demonstrates an average error rate of approximately 3%.

ROCK MECHANICS AND ROCK ENGINEERING (2022)

添加到收藏夹

Article Environmental Sciences

A system of the granite weathering degree assessment using hyperspectral image and CNN

Jaewon Kim et al.

Summary: This study utilizes hyperspectral imaging and a Convolutional Neural Network (CNN) to assess the degree of rock weathering. The results show a high level of accuracy in evaluating the weathering degree of granite without the need for specialized human expertise.

INTERNATIONAL JOURNAL OF MINING RECLAMATION AND ENVIRONMENT (2022)

添加到收藏夹

Article Engineering, Geological

被撤回的出版物: Novel Rock Image Classification: The Proposal and Implementation of RockNet (Retracted article. See FEB, 2023)

Yimeng Zhou et al.

Summary: Rock classification is crucial for geosciences and geological engineering practices. This study introduces RockNet, a next-generation convolutional neural network (CNN), to automatically classify rock types with high accuracy, using computer vision-based artificial intelligence technology.

ROCK MECHANICS AND ROCK ENGINEERING (2022)

添加到收藏夹

Article Construction & Building Technology

Using field data and operational constraints to maximize hard rock TBM penetration and advance rates

Ebrahim Farrokh

Summary: This paper investigates the influence of rock type and uniaxial compressive strength on cutter penetration, providing guidelines for optimal field cutter spacing. The study finds that the cutter spacing should be close to 90 mm for uniaxial compressive strengths below 50 MPa, and below 80 mm for strengths above 150 MPa. The evenly distributed cutterhead layout design is found to be successful even in softer rocks, and an extension of the openings beyond 50% of the cutterhead radius may be needed to maximize performance. The results also show that the linear speed of the cutters is correlated with the normal force index and rolling force index.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2022)

添加到收藏夹

Article Geosciences, Multidisciplinary

Deep learning based classification of rock structure of tunnel face

Jiayao Chen et al.

Summary: An automated framework for classifying rock structures of tunnel face based on convolutional neural networks is proposed and shown to be optimal and efficient in terms of efficiency and accuracy through experiments.

GEOSCIENCE FRONTIERS (2021)

添加到收藏夹

Article Engineering, Environmental

Study of common wear prediction models for hard rock TBM disc cutters and comparison with field observation in Kerman water conveyance tunnel

Morteza Karami et al.

Summary: This study examined the empirical models commonly used for predicting disc wear life in hard rock tunneling, highlighting the importance of careful model selection in slightly abrasive rocks. The results showed varying levels of conservatism in the models, with some offering more compatible estimates with rock abrasivity. Additionally, good correlation was found between predicted and actual cutter lives in the Kerman water conveyance tunnel, based on the ratio of rock mass and intact rock strengths, as well as laboratory measures of rock abrasivity.

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT (2021)

添加到收藏夹

Article Geochemistry & Geophysics

VP and VS prediction from digital rock images using a combination of U-Net and convolutional neural networks

Rongang Cui et al.

Summary: The combination of U-Net and CNN in CUCNN improves the accuracy and efficiency of predicting elastic parameters from digital rock images with limited training data. The R-2 score of CUCNN is 0.84, which increased by 0.21 compared to the conventional CNN.

GEOPHYSICS (2021)

添加到收藏夹

Article Engineering, Petroleum

Sensitivity of Digital Rock Method for Pore-Space Estimation to Heterogeneity in Carbonate Formations

Ravi Sharma et al.

SPE JOURNAL (2021)

添加到收藏夹

Article Construction & Building Technology

Quantification of water inflow in rock tunnel faces via convolutional neural network approach

Jiayao Chen et al.

Summary: The paper presents a novel convolutional neural network-based method for evaluating water inflow in rock tunnel faces, which achieves accurate quantification through classification and segmentation steps. Experimental results demonstrate excellent performance in terms of speed, accuracy, and segmentation capability.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Engineering, Environmental

Evaluating the influence of engineering geological parameters on TBM performance during grinding process in limestone strata

Seyed Mahdi Pourhashemi et al.

Summary: This study evaluated and analyzed the relationships between rock properties and TBM performance parameters in grinding-dominated mode. By statistical analysis, simple empirical equations were developed to accurately predict TBM performance in similar geological conditions where grinding is dominant.

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT (2021)

添加到收藏夹

Article Thermodynamics

Research on rock breaking mechanism and load characteristics of TBM cutter based on discrete element method

Jingxiu Ling et al.

Summary: Through experiments and simulation, this paper established a cutter rock simulation model and analyzed the impact of cutter pole diameter and spacing on rolling force and lateral force. The research results can provide reference for TBM cutter layout and design.

ADVANCES IN MECHANICAL ENGINEERING (2021)

添加到收藏夹

Article Construction & Building Technology

Classification of rock fragments produced by tunnel boring machine using convolutional neural networks

Zhe Yang et al.

Summary: This study used a modified convolutional neural network (CNN) AlexNet to classify rock fragmentation at tunnel construction sites based on images. Experimental results showed that the extracted features are reliable and can accurately detect large rock fragments.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Engineering, Geological

Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning

Jiayao Chen et al.

Summary: This study proposes an image-based method for automated rock fracture segmentation and fracture trace quantification, using the FraSegNet model, skeleton extraction algorithm, and polyline approximation algorithm. The research shows that the method outperforms other deep learning approaches and traditional image edge detection algorithms in extracting fracture trace maps and reducing noise, and the quantitative evaluation proves its effectiveness.

INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Failure Characteristics of Rock Sample during Penetration Tests with the Assistance of Different Free Surface Combinations

Futong Xu et al.

Summary: The study shows that different free surface combinations have different impacts on rock breaking, and free surface-assisted rock breaking can reduce energy consumption.

LITHOSPHERE (2021)

添加到收藏夹

Article Engineering, Geological

A Closer Look into Chip Shape/Size and Efficiency of Rock Cutting with a Simple Chisel Pick: A Laboratory Scale Investigation

Mehdi Mohammadi et al.

ROCK MECHANICS AND ROCK ENGINEERING (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

Fracture characterization and permeability prediction by pore scale variables extracted from X-ray CT images of porous geomaterials

Zhao Zhi et al.

SCIENCE CHINA-TECHNOLOGICAL SCIENCES (2020)

添加到收藏夹

Article Engineering, Geological

From Exploratory Tunnel to Base Tunnel: Hard Rock TBM Performance Prediction by Means of a Stochastic Approach

Andrea Rispoli et al.

ROCK MECHANICS AND ROCK ENGINEERING (2020)

添加到收藏夹

Article Computer Science, Information Systems

Rotation-Invariant Wafer Map Pattern Classification With Convolutional Neural Networks

Seokho Kang

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Research on Intelligent Identification of Rock Types Based on Faster R-CNN Method

Xiaobo Liu et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

How is Gaze Influenced by Image Transformations? Dataset and Model

Zhaohui Che et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Engineering, Geological

Analysis on the Evolution of Rock Block Behavior During TBM Tunneling Considering the TBM-Block Interaction

Zixin Zhang et al.

ROCK MECHANICS AND ROCK ENGINEERING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A systematic study of the class imbalance problem in convolutional neural networks

Mateusz Buda et al.

NEURAL NETWORKS (2018)

添加到收藏夹

Article Automation & Control Systems

The multi-stage rock fragmentation load prediction model of tunnel boring machine cutter group based on dense core theory

Junzhou Huo et al.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2017)

添加到收藏夹

Article Geography, Physical

A multi-scale plane-detection method based on the Hough transform and region growing

Xiaoxu Leng et al.

PHOTOGRAMMETRIC RECORD (2016)

添加到收藏夹

Article Construction & Building Technology

Risk analysis using fault-tree analysis (FTA) and analytic hierarchy process (AHP) applicable to shield TBM tunnels

Ki-Chang Hyun et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2015)

添加到收藏夹

Article Optics

Rock fracture edge detection based on quaternion convolution by scale multiplication

Jiangyan Xu et al.

OPTICAL ENGINEERING (2009)

添加到收藏夹

Article Engineering, Electrical & Electronic

Automated estimation of rock fragment distributions using computer vision and its application in mining

RA Salinas et al.

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.