• 한국지반공학회지:지반
• /
• 제13권5호
• /
• pp.101-124
• /
• 1997

The root pile system is insitu soil reinforcement technique that uses a series of reticulately installed micropiles. In terms of mechanical improvement by means of grouted reinform ming elements, the root pile system is similar to the soil nailing system. The main difference between root piles and soil nailing are due to the fact that the reinforcing bars in root piles are normally grouted under high pressure and that the alignments of the reinforcing members differ. Recently, the root pile system has been broadly used to stabilize slopes and retain excavations. The accurate design of the root pile system is, however, a very difficult tass owing to geometric variety and statical indetermination, and to the difficulty in the soilfiles interaction analysis. As a result, moat of the current design methods have been heavily dependent on the experiences and approximate approach. This paper proposes a quasi-three dimensional method of analysis for the root pile system applied to the stabilization of slopes. The proposed methods of analysis include i) a technique to estimate the change in borehole radium as a function of the grout pressure as well as a function of the time when the grout pressure is applied, ii) a technique to evaluate quasi -three dimensional limit-equilibrium stability for sliding, iii) a technique to predict the stability with respect to plastic deformation of the soil between adjacent root piles, and iv) a quasi -three dimensional finite element technique to compute stresses and dis placements of the root pile structure barred on the generalized plane strain condition and composite unit cell concept talon형 with considerations of the group effect and knot effect. By using the proposed technique to estimate the change in borehole radius as a function of the grout pressure as well as a function of the time, the estimations are made and compar ed with the Kleyner 8l Krizek's experimental test results. Also by using the proposed quasi-three dimensional analytical method, analyses have been performed with the aim of pointing out the effects of various factors on the interaction behaviors of the root pile system.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1997년도 봄 학술발표회 논문집
• /
• pp.47-54
• /
• 1997

• Steel and Composite Structures
• /
• 제48권2호
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).