Abstract
Accurate and quick prediction of UCS values of rocks ahead of one tunnel provides a reliable guarantee for the safety and economy of tunnel construction. The objective of this paper is to investigate the effect of different rock geological conditions on the prediction performance of the developed genetic algorithm optimization of artificial neural network model when predicting uniaxial compressive strength using measurement-while-drilling data. Firstly, the objective tunnel is divided into four sections based on the geological conditions of the rock mass. Secondly, prediction model for each section is developed. Finally, the prediction accuracy of each section is compared and analysed. The results show that the sections with better geological conditions obtain superior prediction performance. In addition, a larger sample dataset has a positive effect on the prediction performance.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.