RETRACTED ARTICLE: Forecasting of Rock Drillability Using a New Computational Intelligent Method

  • PDF / 380,883 Bytes
  • 10 Pages / 547.087 x 737.008 pts Page_size
  • 23 Downloads / 164 Views

DOWNLOAD

REPORT


(0123456789().,-volV) ( 01234567 89().,-volV)

ORIGINAL PAPER

Forecasting of Rock Drillability Using a New Computational Intelligent Method Hadi Fattahi . Nasim Bayat

Received: 11 February 2019 / Accepted: 30 May 2019  Springer Nature Switzerland AG 2019

Abstract A full recognition of the role of rock drillability plays a significant role in drilling parameters optimization, bit selection and prediction of penetration rate in rock drilling projects. However, the traditional forecasting methods, such as empirical formulae, are inaccurate because most of them do not take into consideration all the relevant factors. In this paper, new intelligence method, namely relevance vector regression (RVR) optimized by artificial bee colony (ABC) algorithm is introduced to forecast the unseen data. In this model, diametral point load strength index (Is(50) ?), uniaxial compressive strength, shore scleroscope hardness, Brazilian tensile strength and axial point load strength index (Is(50);)) were utilized as the input parameters, while the rock drillability was the output parameter. The performances of the proposed predictive model was examined according to two performance indices, i.e., coefficient of determination (R2) and mean square error (MSE). The obtained results of this study indicated that the RVR-ABC model is a reliable method to forecast rock drillability with a higher degree of accuracy (R2 = 0.9363 and MSE = 0.01354).

H. Fattahi (&)  N. Bayat Department of Mining Engineering, Arak University of Technology, Arak 1000780654, Iran e-mail: [email protected]

Keywords Rock drillability  Relevance vector regression  Artificial bee colony  Forecasting  Drilling

1 Introduction Rock drillability is a comprehensive index which reflects the capacity of anti-crushing in drilling process (Pingping 2013). Rock drillability is dependent on drilling process parameters in addition to the physico-mechanical properties of the rock being drilled. Rock drillability is widely used in bit type selection, plan for production quotas, formation classification (Chen and Guan 2000). Rock drillability is defined as the penetration rate of a drill bit into the rock. It is a property that cannot be accurately defined by a single mechanical property of the rock, such as uniaxial compressive strength (UCS) or tensile strength. It is a function of several rock properties such as grain size, degree of weathering, mineral composition and texture. Thus several empirical methods have been developed for predicting drilling performance in different rocks (Yarali and Kahraman 2011). Rock drillability was originally developed for the prediction of penetration rate of percussive drills. It was developed in 1950 s and has been applied also for tunnel boring since 1972. The rock drillability is not a direct indicator of drilling rate in the field, but it is a relative measure of penetration rate and it is

123

Geotech Geol Eng

therefore not an absolute value of the drilling rate in the site. It may also be viewed as a parameter for the maximu