Prediction of TBM jamming risk in squeezing grounds using Bayesian and artificial neural networks

Hasanpour, Rohola; Rostami, Jamal; Schmitt, Jürgen; Özçelik, Yılmaz; Sohrabian, Babak

doi:10.1016/j.jrmge.2019.04.006

Cited by 65 publications

(26 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pollock et al [26] have used machine learning algorithms to improve the efficiency of directional drilling (rate of penetration optimization, lowering tortuous borehole, lowering the number personnel on board and improving consistency across operations). Bayesian network (BN) and ANN have been successfully used for risk assessment in trenchless construction projects applying tunnelling technology e.g., risk assessment of road tunnels [27], risk analysis of construction of Porto Metro tunnel [28], risk assessment of damage to existing surface properties caused by tunnelling [29], safety risk assessment for metro construction projects [30], as well as evaluation of jamming risk of the shielded tunnel boring machines in adverse ground conditions such as squeezing grounds [31].…”

Section: Review Of Literature and Limitations Of The Previous Workmentioning

confidence: 99%

Risk Assessment in Energy Infrastructure Installations by Horizontal Directional Drilling Using Machine Learning

Krechowicz

2021

Energies

View full text Add to dashboard Cite

Nowadays we can observe a growing demand for installations of new gas pipelines in Europe. A large number of them are installed using trenchless Horizontal Directional Drilling (HDD) technology. The aim of this work was to develop and compare new machine learning models dedicated for risk assessment in HDD projects. The data from 133 HDD projects from eight countries of the world were gathered, profiled, and preprocessed. Three machine learning models, logistic regression, random forests, and Artificial Neural Network (ANN), were developed to predict the overall HDD project outcome (failure free installation or installation likely to fail), and the occurrence of identified unwanted events. The best performance in terms of recall and accuracy was achieved for the developed ANN model, which proved to be efficient, fast and robust in predicting risks in HDD projects. Machine learning applications in the proposed models enabled eliminating the involvement of a group of experts in the risk assessment process and therefore significantly lower the costs associated with the risk assessment process. Future research may be oriented towards developing a comprehensive risk management system, which will enable dynamic risk assessment taking into account various combinations of risk mitigation actions.

show abstract

Section: Review Of Literature and Limitations Of The Previous Workmentioning

confidence: 99%

Risk Assessment in Energy Infrastructure Installations by Horizontal Directional Drilling Using Machine Learning

Krechowicz

2021

Energies

View full text Add to dashboard Cite

show abstract

“…For the structural design and vibration reduction optimization of the cutterhead system. Liu, 14 Hasanpour et al, 15,16 and Afrasiabi et al 17–23 were devoted to studying various performance parameters that affect the work of TBM, such as rock parameters and machine parameters to establish prediction theoretical models of TBM performance. Methods such as “penalty factor” and “pso-ann hybrid model” were proposed to estimate the performance of TBM, which enriched the theoretical model of intelligent prediction.…”

Section: Introductionmentioning

confidence: 99%

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

Ling

Cheng

Tong

et al. 2021

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Tunnel boring machine (TBM) is a large-scale tunnel engineering equipment, which has unparalleled advantages in safety and work efficiency. The cutter is subjected to complex and variable random impact loads, resulting in damage to bearings, cutter rings, and cutter shafts. Therefore, based on the discrete element simulation platform and experiment, this paper established the cutter rock simulation model based on the experimental data, and analyzed the rock breaking process, cutter load magnitude, and variation law. The research results show that when the cutter pole diameter decreases from 200 mm, 100 mm, and 0 mm in sequence, the rolling force increases accordingly, and the maximum increase of the rolling force is 56%. Meanwhile the lateral force decreases and the maximum average decrease value is 26%. Moreover, the rolling force showed a downward trend with the increase of the cutter spacing. When the cutter spacing is increased from 80 mm to 120 mm, the average rolling force decreases by 51%, and the maximum value rises slightly, increasing by 2%. And, the lateral force tends to increase, with an increase of 17% and the maximum lateral force value increase was 29%. The results can provide load input reference for TBM cutter layout, cutterhead structure design, and performance evaluation.

show abstract

“…A new structured was developed to for prediction of TBM jamming risk in squeezing ground by using Bayesian and ANN (Hasanpour et al, 2019). As part of neural network transaction method if any error occurs in the training this goes backward.…”

Section: Introductionmentioning

confidence: 99%

Application of an artificial neural network for predicting compressive and flexural strength of basalt fiber added lightweight concrete

Çaliş¹,

Yıldızel²,

Keskin³

2021

CJCRL

View full text Add to dashboard Cite

Concrete is known as one of the fundamental materials in construction with its high amount of use. Lightweight concrete (LWC) can be a good alternative in reducing the environmental effect of concrete by decreasing the self-weight and dimensions of the structure. In order to reduce self-weight of concrete artificial aggregates, some of which are produced from waste materials, are utilized, and it also contributes to develop a sustainable material Artificial neural networks have been the focus of many scholars for long time with the purpose of analyzing and predicting the lightweight concrete compressive and flexural strengths. The artificial neural network is more powerful method in terms of providing explanation and prediction in engineering studies. It is proved that the error rate of ANN is smaller than regression method. Furthermore, ANN has superior performance over nonlinear regression model. In this paper, an ANN based system is proposed in order to provide a better understanding of basalt fiber reinforced lightweight concrete. In the regression analysis predicted vs. experimental flexural strength, R-sqr is determined to be 86%. The most important strength contributing factors were analyzed within the scope of this study.

show abstract

Prediction of TBM jamming risk in squeezing grounds using Bayesian and artificial neural networks

Cited by 65 publications

References 24 publications

Risk Assessment in Energy Infrastructure Installations by Horizontal Directional Drilling Using Machine Learning

Risk Assessment in Energy Infrastructure Installations by Horizontal Directional Drilling Using Machine Learning

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

Application of an artificial neural network for predicting compressive and flexural strength of basalt fiber added lightweight concrete

Contact Info

Product

Resources

About