Prediction of geological conditions for a tunnel boring machine using big operational data

Zhang, Qianli; Liu, Zhenyu; Tan, Jianrong

doi:10.1016/j.autcon.2018.12.022

Cited by 174 publications

(40 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for monitoring tasks), clustering (e.g. to identify structures within data [26] using K-Means clustering to identify rock mass types based on TBM operational data) or dimensionality reduction (e.g. to visualize high dimensional space [25] using dimension reduction to improve the performance of geophysical log data classification).…”

Section: Will Enablementioning

confidence: 99%

Machine Learning in tunnelling – Capabilities and challenges

Marcher

Erharter

Winkler

2020

Geomechanics and Tunnelling

View full text Add to dashboard Cite

Digitalization will change the way of gathering geological data, methods of rock classification, application of design analyses in the field of tunnelling as well as tunnel construction and maintenance processes. In recent years, a rapid increase in the successful application of digital techniques (Building Information Modelling and Machine Learning (ML)) for a variety of challenging tasks has been observed. Driven by the increasing overall amount of data combined with the easy availability of more computing power, a sharp increase in the successful deployment of techniques of ML has been seen for different tasks. ML has been introduced in many sciences and technologies and it has finally arrived in the fields of geotechnical engineering, tunnelling and engineering geology, although still not as far developed as in other disciplines. This paper focuses on the potential of ML methods for geotechnical purposes in general and tunnelling in particular. Applications such as automatic rock mass behaviour classification using data from tunnel boring machines (TBM), updating of the geological prognosis ahead of the tunnel face, data driven interpretation of 3D displacement data or fully automatic tunnel inspection will be discussed.

show abstract

Section: Will Enablementioning

confidence: 99%

Machine Learning in tunnelling – Capabilities and challenges

Marcher

Erharter

Winkler

2020

Geomechanics and Tunnelling

View full text Add to dashboard Cite

show abstract

“…And the amplitude and spatial distribution of the soil displacement can be then obtained with data records. Geological information is a key factor in safety management of tunnel construction, and different methods including ANN [31] and support vector classifier (SVC) [32] has been proposed to predict geological formation based on TBM operating data. Shi et al [33], [34] proposed a fuzzy c-means algorithm to cluster TBM monitoring data.…”

Section: Literature Review a Data Analysis In Tbm And Tunnel Engmentioning

confidence: 99%

A Hybrid Data Mining Method for Tunnel Engineering Based on Real-Time Monitoring Data From Tunnel Boring Machines

Leng

Lin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Tunnel engineering is one of the typical megaprojects given its long construction period, high construction costs and potential risks. Tunnel boring machines (TBMs) are widely used in tunnel engineering to improve work efficiency and safety. During the tunneling process, large amount of monitoring data has been recorded by TBMs to ensure construction safety. Analysis of the massive real-time monitoring data still lacks sufficiently effective methods and needs to be done manually in many cases, which brings potential dangers to construction safety. This paper proposes a hybrid data mining (DM) approach to process the realtime monitoring data from TBM automatically. Three different DM techniques are combined to improve mining process and support safety management process. In order to provide people with the experience required for on-site abnormal judgement, association rule algorithm is carried out to extract relationships among TBM parameters. To supplement the formation information required for construction decisionmaking process, a decision tree model is developed to classify formation data. Finally, the rate of penetration (ROP) is evaluated by neural network models to find abnormal data and give early warning. The proposed method was applied to a tunnel project in China and the application results verified that the method provided an accurate and efficient way to analyze real-time TBM monitoring data for safety management during TBM construction. INDEX TERMS Data mining, monitoring data, tunnel boring machine (TBM), tunnel construction, underground structure.

show abstract

“…Once deployed, the analysis of the performance continues and enormous data gets generated during the process. This leads to issues like big data handling and can be taken care of by methods like balanced iterative reducing and clustering using hierarchies [71].…”

Section: Selection Of Tbm On the Basis Of Different Geological Conditmentioning

confidence: 99%

Influence of geology on tunnel boring machine performance: A review

Pandey¹,

Raina²,

Deshmukh³

et al. 2020

J Min & Metal A Mining

View full text Add to dashboard Cite

Tunnel boring machines are used for excavating a variety of soils and rocks for circular cross-section tunnels. Several published studies examined the role of rockmass in determining the cutting and advance rate of tunnel boring machines. A comprehensive review of literature was conducted to ascertain the influence of geological conditions on the performance of tunnel boring machines and revealed that different rock characteristics were used to define the tunnel boring machine performance. The progress of the tunnel boring machine was ascribed to the inherent properties of the rockmass, intact rock properties, and surrounding geological conditions. Several authors found that extreme geological conditions strongly influence the advance of the machine. The review revealed that joint spacing, angle between plane of weakness and tunnel axis, rock quality designation, and number of joint sets were the most important variables that influenced the advance rates of the tunnel boring machine. At least 12 intact rock variables were used to define tunnel boring machine performance with one to seven such variables used in combination. The compressive strength, tensile strength, and brittleness index emerged as most crucial intact properties. Rockmass classifications or indices of tunnel boring machine performance were used by different authors to predict their performance and even to define their selection methodology. Use of dynamic properties of rock/rockmass was identified as a grey area for future research by scientists.

show abstract

Prediction of geological conditions for a tunnel boring machine using big operational data

Cited by 174 publications

References 32 publications

Machine Learning in tunnelling – Capabilities and challenges

Machine Learning in tunnelling – Capabilities and challenges

A Hybrid Data Mining Method for Tunnel Engineering Based on Real-Time Monitoring Data From Tunnel Boring Machines

Influence of geology on tunnel boring machine performance: A review

Contact Info

Product

Resources

About