An ANN to Predict Ground Condition ahead of Tunnel Face using TBM Operational Data

• Published in: KSCE journal of civil engineering Vol. 23; no. 7; pp. 3200 - 3206
• Main Authors: Jung, Jee-Hee, Chung, Heeyoung, Kwon, Young-Sam, Lee, In-Mo
• Format: Journal Article
• Language: English
• Published: Seoul Korean Society of Civil Engineers 01.07.2019; Springer Nature B.V; 대한토목학회
• Subjects: Accuracy; Algorithms; Architectural engineering; Artificial neural networks; Back propagation; Boring machines; Civil Engineering; Data; Data acquisition; Disclaimers; Drilling & boring machinery; Engineering; Geotechnical Engineering & Applied Earth Sciences; Industrial Pollution Prevention; Mathematical models; Methods; Model accuracy; Neural networks; Predictions; Trends; Tunnel construction; Tunnel Engineering; Tunneling shields; Tunnels; 토목공학; artificial neural network (ANN); tunnel boring machine (TBM); ground types; backpropagation (BP) algorithm; tunnel face; TBM data; ground condition prediction
• ISSN: 1226-7988; 1976-3808
• DOI: 10.1007/s12205-019-1460-9

This paper presents an artificial neural network (ANN) model that predicts ground conditions ahead of a tunnel face by using shield tunnel boring machine (TBM) data obtained during the tunneling operation. The primary advantage of the proposed technique is that, by using TBM data, no additional data acquisition device is required. Ground type classifications and machine data normalization methods are introduced to maintain the consistency of the measured data and improve prediction accuracy. The efficacy of the proposed model is demonstrated by its 96% accuracy in predicting ground type one ring ahead of the tunnel face.