Neuro-fuzzy identification of drilling control system adapted to rock types

The research is aimed at investigating methods of forming a model for the system of adaptive control for drilling with a control object identifier. Under rapidly changing conditions of borehole drilling it is expedient to apply a strategy of the two-level adaptive control, which implies simultaneous drilling investigation and control. The subsystem of prediction is implemented on the basis of an adaptive neuro-fuzzy system. The applied neuro-fuzzy system realizes the Sugeno fuzzy inference in the form of a five-layer neural network of signal feedforward, the first layer of which contains the terms of input variables (the current signal value and its delayed values). It should be noted that the membership function type did not influence much the prediction result. While processing and analyzing the current information on the latest characteristics of drilling and while forming the adaptive control it is reasonable to apply neuro-fuzzy structures with the Gaussian membership functions.

[1]  Ultrasonic testing of pulp solid phase concentration and particle size distribution considering dispersion and dissipation influence , 2015 .

[2]  K. Yin,et al.  Using Information Extracted From Drill Data to Improve Blasting Design and Fragmentation , 2001 .

[3]  Malcolm Scoble,et al.  Correlation beween rotary drill performance parameters and borehole geophysical logging , 1989 .

[4]  Sildomar T. Monteiro,et al.  Conditional Random Fields for Rock Characterization Using Drill Measurements , 2009, 2009 International Conference on Machine Learning and Applications.

[5]  Håkan Schunnesson,et al.  Rock characterisation using percussive drilling , 1998 .

[6]  Leslie George Tham,et al.  Automatic monitoring of rotary-percussive drilling for ground characterization—illustrated by a case example in Hong Kong , 2004 .

[7]  Håkan Schunnesson,et al.  Drill monitoring for geological mine planning in the Viscaria copper mine, Sweden , 1997 .

[8]  Detlef Nauck,et al.  Foundations Of Neuro-Fuzzy Systems , 1997 .

[9]  S. Kahramana,et al.  Dominant rock properties affecting the penetration rate of percussive drills , 2003 .

[10]  Vitaliy Tron,et al.  Model synthesis of nonlinear nonstationary dynamical systems in concentrating production using Volterra kernel transformation , 2015 .

[12]  J. L. B. Segui,et al.  Blast design using measurement while drilling parameters , 2002 .

[13]  H. Liu,et al.  Analysis and Interpretation of Monitored Rotary Blasthole Drill Data , 2001 .