Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44175

Estimation of Rock Joint Trace Length in Scanline Sampling Using Artificial Neural Network (ANN)

Jamal Zadhesh, Abbas Majdi


Geometrical modeling of jointed rock massneeds the geometrical parameters of joints such as orientation, spacing, trace length, shape, and location.The trace length of rock joints is an important design parameter in rock engineering and geotechnics because affecting rock mass strength. It controlsthe stability of the rock slope and tunnels in jointed rock masses. This parameter is usually determined through a joint survey in the field. It is complicated to obtain the parameters because a complete joint plane within rock mass cannot be observed directly. Thedevelopment of predictive models to determinerock joint length seems to be essential in rock engineering.In this paper, an attempt was made to develop an artificial neural network (ANN) modelto predict rock joint length. For this aim, a database of scanline joint sampling of Sarshiw andesites in Iran was surveyed, whichintersection distance of the joint on the scanline, spacing, aperture, orientation (dip and dip direction), roughness, Schmidt rebound of the joint’s wall, type of joint termination, joint trace lengths in both sides of the scanline were measured. Final results indicated that this technique could predict joint trace length with high R2 and minimum RMSE equal to 0.8667 and 1.93,respectively


Rock Joint, Joint Trace Length, Scanline Sampling, Artificial Neural Network.

Full Text