Predicting Intelligence Using Hybrid Artificial Neural Networks in Context-Aware Tunneling Systems under Risk and Uncertain Geological Environment

Abstract

In pervasive computing environments the availability of real-time computation models is expected to predict a performance of Tunnel Boring Machine (TBM). Context awareness allows an entity adapt to uncertain environment, offering a number of intelligent prediction methods for tunneling. This study presents a proposal of a Context-Aware Tunneling System using Hybrid Artificial Neural Networks for prediction of TBM performance and risk response in uncertain geological environments. The proposed approach is essential to predict the TBM performance, together warning disaster risks in terms of the performance and risk response for the planning projects of tunneling. In addition, the proposed approach aims to predict TBM performance and utilization through a network in complex underground conditions such as rock mass, geology, lithography, and disaster in tunnel projects. The proposed approach has tested in experiments using data series from tunnel projects in Japan and Asian countries. To validate the significance of the findings and show added valuable parameters of the proposed approach, the results are compared with conventional statistical methods in terms of TBM performance evaluation. In order to evaluate the effectiveness of this approach, experimental results show that the proposed approach performs better than other current methods under uncertain geological environments.