Basarir, H, Wesseloo, J, Karrech, A, Pasternak, E & Dyskin, A 2017, 'The use of soft computing methods for the prediction of rock properties based on measurement while drilling data', in J Wesseloo (ed.), Deep Mining 2017: Proceedings of the Eighth International Conference on Deep and High Stress Mining, Australian Centre for Geomechanics, Perth, pp. 537-551, https://doi.org/10.36487/ACG_rep/1704_36_Basarir
(https://papers.acg.uwa.edu.au/p/1704_36_Basarir/)
Abstract: Due to recent technological advancements drilling operations conducted for different purposes such as exploration, blasting and even grouting are not considered as auxiliary operations any longer. On the contrary, nowadays onsite drilling operations are considered as important resources for getting more information about rock properties. Many researchers have been working on measurement while drilling (MWD) techniques and their possible use for the prediction of rock mass properties.
This paper presents a literature survey on the use of MWD technology for the prediction of rock mass properties. The survey indicates that the analysis and interpretation of MWD data is as important as recording the data. Both blackbox modelling such as regression and soft computing or grey-box modelling techniques are used as a tool for the analysis and interpretation of MWD data. This paper presents a case study showing the integration of soft computing methods such as adaptive fuzzy inference system (ANFIS) with MWD data for the prediction of rock mass properties such as rock quality designation (RQD). The results indicated that such soft computing methods can successfully be used as an analysis and interpretation tool.

Keywords: measurement while drilling (MWD), adaptive neuro fuzzy inference system (ANFIS), rock quality designation (RQD), soft computing