TBM data processing is an important aspect that affects several phases of the construction process of a tunnel excavated by TBM. The real-time machine monitoring is required during the excavation phase, and the TBM data are used after the tunnel completion to gather information for predictions in new tunnel projects. The main issues typically involved in TBM data processing include the raw data management and filtering, the implementation of the rock mass data, and the machine performance evaluation. The paper presents a series of procedures for dealing with the TBM data processing in hard rock context, starting from the raw data provided by the machine acquisition system. Guidelines for an efficient data filtering are provided, together with techniques to improve the representativeness of the data sample. Several techniques for analysing and modelling the datasets are reported, including descriptive statistics, regression analysis and neural net fitting. An approach to carry out probabilistic analysis on the TBM parameters is also described.
TBM data processing for performance assessment and prediction in hard rock / Rispoli, A.; Ferrero, A. M.; Cardu, M.. - ELETTRONICO. - (2019), pp. 2940-2949. (Intervento presentato al convegno World Tunnel Congress - WTC 2019 tenutosi a Napoli nel 5-9 maggio) [10.1201/9780429424441-311].
TBM data processing for performance assessment and prediction in hard rock
A. Rispoli;A. M. Ferrero;M. Cardu
2019
Abstract
TBM data processing is an important aspect that affects several phases of the construction process of a tunnel excavated by TBM. The real-time machine monitoring is required during the excavation phase, and the TBM data are used after the tunnel completion to gather information for predictions in new tunnel projects. The main issues typically involved in TBM data processing include the raw data management and filtering, the implementation of the rock mass data, and the machine performance evaluation. The paper presents a series of procedures for dealing with the TBM data processing in hard rock context, starting from the raw data provided by the machine acquisition system. Guidelines for an efficient data filtering are provided, together with techniques to improve the representativeness of the data sample. Several techniques for analysing and modelling the datasets are reported, including descriptive statistics, regression analysis and neural net fitting. An approach to carry out probabilistic analysis on the TBM parameters is also described.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2740792
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo