Fuzzy Modeling Approaches for the Prediction of Machine Utilization in Hard Rock Tunnel Boring Machines

The main objective of this paper was to develop a TBM utilization predictor model by using fuzzy logic. Rule-based (Mamdani model) and parametric-based (Sugeno model) fuzzy logic were adapted to model subjective and unquantified TBM field data sets. A total of three hard TBM projects were studied to establish possible trends and correlations between rock mass properties and machine utilization. Since rock mass properties are the most affecting and unpredictable factors to machine utilization, only rock mass properties were focused and analyzed in this paper. The identification of input parameters includes: machine diameter, RMR, groundwater inflow rate, and RQD. These were used as input parameters influencing machine utilization level for both algorithms. In order to verify the validity of the two models, the predicted machine utilization level and the measured (or real) utilization level from the field records were compared. The Sugeno model was a more accurate estimator of machine utilization than Mamdani's, with a smoother resolution. By applying this utilization predictor model for the planning stage of TBM projects, a machine advance rate and corresponding total excavation time and cost can be estimated and be used as a useful tool for TBM project planning and bidding purpose.