No abstract

No abstract

This paper proposes a new fuzzy regression model, i.e., the fuzzy system constructed by rule generation and iterative linear support vector regression (FS-RGLSVR) for structural risk minimization. The FS-RGLSVR is composed of Takagi-Sugeno (TS)-type fuzzy IF-THEN rules. These rules are automatically constructed by a self-splitting rule generation algorithm that introduces the self-splitting technique to the k-means clustering algorithm. This new algorithm regards a cluster as a fuzzy rule, where no preassignment of the cluster (rule) number is necessary. The cost function for parameter learning is defined based on structural risk instead of empirical risk minimization in order to achieve generalizability. Tuning all of the free parameters in the FS-RGLSVR using linear support vector regression (SVR) is proposed to minimize the cost function. Each of the consequent and antecedent part parameters is expressed as a linear combination coefficient in a transformed input space so that the linear SVR is applicable. This paper introduces iterative linear SVR to tune antecedent and consequent parameters. This paper demonstrates the capabilities of FS-RGLSVR by two simulated and four practical regression examples. Comparisons with fuzzy systems with different types of learning algorithms verify the performance of the FS-RGLSVR

This paper provides a summary report on measures taken to remove embedded steel ‘H' pile obstacles from the cutter head of an advancing tunnel-boring machine. The piles were part of the soil-mixing retaining wall built for the cut-and-cover tunnel construction of a Taiwan high-speed rail tunnel and a Taiwan railways administration tunnel, which were directly above the mass rapid transit tunnel that was to be constructed. The collision zone between the boring machine and piles was below groundwater level and was approximately 23 m below the ground surface in a silty sand layer. To remove the piles safely from the cutter head, horizontal grouting from two adjacent work pits was conducted for waterproofing and solidification purposes. By controlling the amount of soil being flushed out during the grout hole drilling first, and also the pressure used for grouting later, the measured tunnel settlement resulting from grouting was negligible. Because of the favourable watertightness of the grouted zone and the dewatering influence of a nearby construction site, pile removal was conducted under particularly dry working conditions. In total, 12 piles were identified in the collision zone and were successfully removed from the cutter head by hand tools.