Skip to Main Content
In this paper, we focus on two questions common in tunneling project:(i) how to identify the unmeasured stratum; (ii) how to make the project safe under the uncertain condition automatically. The basic ideal of the presented approach is to establish a soil identification model with statistical information of geological site investigation and then to update the model with Field Penetration Index (FPI) and Torque Penetration Index (TPI) extracted from shield machine tunneling process data. Based on this soft-sensor model, project risk can be evaluated and controlled with process monitoring techniques, work experience and other measures. Belief rule-base inference methodology using the evidential reasoning (RIMER) approach is introduced to establish this system, as the following advantages which make it possible to provide a more accurate result than traditional IF-THEN rule-base method: (i) a new rule base knowledge representation scheme which is designed with belief degrees embedded in all possible consequents of a rule; (ii) the inference in such a rule base is implemented using the evidential reasoning (ER) approach. A numerical example is provided to illustrate the potential applications of the proposed methodology.