A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
GFII: A new index to identify geological features during shield tunnelling
https://orcid.org/0000-0002-5610-7988
https://orcid.org/0000-0001-5209-5169
Graphical abstract Display Omitted
Highlights A new index (GFII) was proposed based on force analysis on shield to identify geological features. Weights of various shield parameters affected by geological features were analysed. Results of geological identification by the GFII and machine learning were compared. A case study in Guangzhou was employed to verify the high effectiveness of the GFII.
Abstract Geological features play an essential role in ensuring the safety and enhancing the construction efficiency of shield tunnelling. However, owing to the concealed nature of the excavation environment, these features remain unobservable. Relying on a single shield parameter is insufficient to determine these geological features owing to the lack of detailed geological data. Consequently, a novel index, called geological feature identification index (GFII), has been introduced. This index incorporates shield parameters and employs various weighting techniques. First, the forces exerted on the shield machine throughout the tunnelling process are analysed. The shield parameters obtained from field recordings and their corresponding weights, which are affected by geological features, are evaluated using different weighting techniques. Subsequently, the GFII is used to assign index value to the geological conditions based on their resistance to the tunnelling procedure. The results reveal that both cutterhead torque and shield thrust weights are profoundly influenced by various geological features. Notably, the entropy-weighted GFII shows superior performance, evidencing a minimal overlap rate (19.4%) for hard rock. Thus, GFII can better represent the geological features compared to the fuzzy C-means algorithm classification and other existing indices. Furthermore, any pronounced fluctuation in the GFII may indicate the severity of the wear conditions of disc cutters. Therefore, GFII can assist engineers in planning shield maintenance schedules.
GFII: A new index to identify geological features during shield tunnelling
https://orcid.org/0000-0002-5610-7988
https://orcid.org/0000-0001-5209-5169
Graphical abstract Display Omitted
Highlights A new index (GFII) was proposed based on force analysis on shield to identify geological features. Weights of various shield parameters affected by geological features were analysed. Results of geological identification by the GFII and machine learning were compared. A case study in Guangzhou was employed to verify the high effectiveness of the GFII.
Abstract Geological features play an essential role in ensuring the safety and enhancing the construction efficiency of shield tunnelling. However, owing to the concealed nature of the excavation environment, these features remain unobservable. Relying on a single shield parameter is insufficient to determine these geological features owing to the lack of detailed geological data. Consequently, a novel index, called geological feature identification index (GFII), has been introduced. This index incorporates shield parameters and employs various weighting techniques. First, the forces exerted on the shield machine throughout the tunnelling process are analysed. The shield parameters obtained from field recordings and their corresponding weights, which are affected by geological features, are evaluated using different weighting techniques. Subsequently, the GFII is used to assign index value to the geological conditions based on their resistance to the tunnelling procedure. The results reveal that both cutterhead torque and shield thrust weights are profoundly influenced by various geological features. Notably, the entropy-weighted GFII shows superior performance, evidencing a minimal overlap rate (19.4%) for hard rock. Thus, GFII can better represent the geological features compared to the fuzzy C-means algorithm classification and other existing indices. Furthermore, any pronounced fluctuation in the GFII may indicate the severity of the wear conditions of disc cutters. Therefore, GFII can assist engineers in planning shield maintenance schedules.
GFII: A new index to identify geological features during shield tunnelling
https://orcid.org/0000-0002-5610-7988
https://orcid.org/0000-0001-5209-5169
Graphical abstract Display Omitted
Highlights A new index (GFII) was proposed based on force analysis on shield to identify geological features. Weights of various shield parameters affected by geological features were analysed. Results of geological identification by the GFII and machine learning were compared. A case study in Guangzhou was employed to verify the high effectiveness of the GFII.
Abstract Geological features play an essential role in ensuring the safety and enhancing the construction efficiency of shield tunnelling. However, owing to the concealed nature of the excavation environment, these features remain unobservable. Relying on a single shield parameter is insufficient to determine these geological features owing to the lack of detailed geological data. Consequently, a novel index, called geological feature identification index (GFII), has been introduced. This index incorporates shield parameters and employs various weighting techniques. First, the forces exerted on the shield machine throughout the tunnelling process are analysed. The shield parameters obtained from field recordings and their corresponding weights, which are affected by geological features, are evaluated using different weighting techniques. Subsequently, the GFII is used to assign index value to the geological conditions based on their resistance to the tunnelling procedure. The results reveal that both cutterhead torque and shield thrust weights are profoundly influenced by various geological features. Notably, the entropy-weighted GFII shows superior performance, evidencing a minimal overlap rate (19.4%) for hard rock. Thus, GFII can better represent the geological features compared to the fuzzy C-means algorithm classification and other existing indices. Furthermore, any pronounced fluctuation in the GFII may indicate the severity of the wear conditions of disc cutters. Therefore, GFII can assist engineers in planning shield maintenance schedules.
GFII: A new index to identify geological features during shield tunnelling
Yan, Tao (author) / Shen, Shui-Long (author) / Zhou, Annan (author)
2023-09-29
Article (Journal)
Electronic Resource
English
Identification of geological characteristics from construction parameters during shield tunnelling
| Springer Verlag | 2023
| UB Braunschweig | 2012
| TIBKAT | 2012
Bored tunnelling - TBM and shield tunnelling
| British Library Conference Proceedings | 2000