International Journal of Rock Mechanics and Mining Sciences
Prediction of hard rock TBM penetration rate using particle swarm optimization
Introduction
The prediction of tunnel boring machine (TBM) performance is one of the complex and crucial tasks encountered frequently to excavate the mechanical tunnels. Estimating the machine performance may reduce the risks related to high capital costs typical for excavation operation [1], [2]. Since the first TBM was built, various prognosis models have been developed based on both intact and mass rock properties together with machine specifications. Prediction of TBM performance requires the assessment of the penetration rate (ROP), the ratio of excavated distance to the operating time during continuous excavation phase and advance rate (AR), and the ratio of both mined and supported actual distance to the total time [1], [2], [3]. Developing the prediction models is one of the main tasks and it has been under progress since many years [2], [4], [5], [6], [7], [8], [9], [10], [11], [12]. Besides these theoretical and empirical models, Artificial Neural Networks (ANN) have been used to predict the rate of penetration [13], [14], [15]. Furthermore, fuzzy logic, genetic algorithms and ANNs have been utilized for establishing predictive models in hydrology, mining and civil engineering applications in recent years [15], [16], [17], [18], [19], [20], [21], [22]. A majority of these models are generated based on the experience gained and the data compiled from the past tunneling projects. Although many models have been produced for estimating the ROP with linear, nonlinear multivariable regression, ANN and fuzzy techniques, there has yet been no attempt made to estimate the rate of penetration using the PSO method.
The aim of the current study is develop a TBM performance prognosis using the particle swarm optimization algorithm. To obtain the goal, the database including strength and brittleness of intact rock, orientation and distance between planes of weakness in the rock mass, machine specifications and performance data, have been established by collecting the field and laboratory data from completed hard rock tunnel in the City of New York, USA. Afterward, using the established dataset, the PSO model is developed for predicting the machine performance by means of the rate of penetration in both fractured and mass rock conditions.
Section snippets
Data collection and data structure
The Queens Tunnel no. 3, stage 2 was studied in both field and laboratory to establish database to develop the PSO model for estimating the TBM penetration. Robbins TBM (235-282) that was equipped with 48.2 cm disk cutters and a rated load capacity of 30 tons per cutter were utilized to excavate around 7.5 km long tunnel of 7.06 m diameter, and roughly 200 m deep through the subsurface of southwestern Queens in the City of New York, USA. The tunnel was constructed between 1997 and 2000 to improve
Procedure for selecting input parameters
Predicting the rate of penetration is a nonlinear and multivariable complex problem that depend on many variables. Thus, it is not easy to be solved with a simple linear regression method. The ROP may depend on various rock properties including strength, brittleness, distance between plane of weakness, orientation of discontinuities and also TBM specifications such as torque, thrust, RPM, disk diameter, etc. So, the problem is highly complicated for a simple linear regression approach. There
Particle swarm optimization algorithm
Particle swarm optimization that was first developed by Kennedy and Eberhart [29] is an evolutionary computation technique to solve a continuous global optimization problem with a nonlinear technique. The particle swarm idea originated as a simulation of a simplified social system, the graceful but unpredictable choreography of a flock of birds. Each individual taking place in the PSO algorithm is a so-called particle, and the population generated by these particles is called a swarm. The key
PSO technique applied for predicting TBM penetration rate
One of the evolutionary computational techniques showing its potential and good aspects for solving various optimization problems is the Particle Swarm Optimization. The PSO technique is introduced to estimate the TBM penetration based on intact and mass rock properties herein. For application of PSO to estimate the TBM penetration, no references seem to exist in the literature, and so this study is the first attempt for this purpose. To achieve the aim, input parameters for development of PSO
Conclusions
In this study, the PSO technique has been utilized for estimating the hard rock TBM penetration rate. It is observed that intact and mass rock properties including the UCS, BI, DPW and alpha angle have major effect on the TBM penetration, while the BTS effect on the result is insignificant. So, the model was generated based on relevant properties.
Seven PSO models were generated using the developed dataset in different ways. In models 1–5, the established dataset is divided into five phase, and
References (41)
Utilizing rock mass properties for predicting TBM performance in hard rock condition
Tunnel Underground Space Tech
(2008)Hard rock tunnel boring: prognosis and costs
Tunnel Underground Space Tech
(1988)- et al.
Verhoef PNW. Modeling tunnel boring machine performance by neuro-fuzzy methods
Tunnel Underground Space Tech
(2000) - et al.
Modeling TBM performance with artificial neural networks
Tunnel Underground Space Tech
(2004) - et al.
Fuzzy model for the prediction of unconfined compressive strength of rock samples
Int J Rock Mech Min Sci
(1999) - et al.
A fuzzy model to predict the uniaxial compressive strength and modulus of elasticity of a problematic rock
Eng Appl Artific Intell
(2004) - et al.
Estimation of rock modules: for intact rock with an artificial neural network and for rock masses with a new empirical equation
Int J Rock Mech Min Sci
(2006) - et al.
Tunneling performance prediction using an integrated GIS and neural network
Comp Geotech
(2007) - et al.
Application of fuzzy inference and non-linear regression methods for predicting rock brittleness
Expert Syst Appl
(2010) Assessment of brittleness using rock strength and density with punch penetration test
Tunnel Underground Space Tech
(2009)
A fuzzy logic model to predict specific energy requirement for TBM performance prediction
Tunnel Underground Space Tech
Identification of visco-elastic models for rocks using genetic programming coupled with the modified particle swarm optimization algorithm
Int J Rock Mech Min Sci
A split-step particle swarm optimization algorithm in river stage forecasting
J Hydrol
Short-term hydro-thermal scheduling using particle swarm optimization method
Energy Conversion Manag
Nonlinear parameter estimation through particle swarm optimization
Chem Eng Sci
Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River
J Hydrol
Particle swarm optimization applied to the design of water supply systems
Comps Math Appl
Design optimization of wastewater collection networks by PSO
Comps Math Appl
Application of two non-linear prediction tools to the estimation of tunnel boring machine performance
Eng Appl Artif Intell
Cited by (181)
Profiling of weathered argillaceous limestone rock with MWD data from advanced drilling for tunnelling along Wu-Kai expressway in Chongqing, China
2024, Tunnelling and Underground Space TechnologyTransfer learning for collapse warning in TBM tunneling using databases in China
2024, Computers and GeotechnicsEvaluation and prediction of earth pressure balance shield performance in complex rock strata: A case study in Dalian, China
2023, Journal of Rock Mechanics and Geotechnical EngineeringStudy on disc cutter chipping of TBM based on field data and particle flow code simulation
2023, Underground Space (China)