A. Kaveh, S. M. Hamze-Ziabari, T. Bakhshpoori,
Volume 8, Issue 1 (1-2018)
Abstract
In the present study, two new hybrid approaches are proposed for predicting peak ground acceleration (PGA) parameter. The proposed approaches are based on the combinations of Adaptive Neuro-Fuzzy System (ANFIS) with Genetic Algorithm (GA), and with Particle Swarm Optimization (PSO). In these approaches, the PSO and GA algorithms are employed to enhance the accuracy of ANFIS model. To develop hybrid models, a comprehensive database from Pacific Earthquake Engineering Research Center (PEER) are used to train and test the proposed models. Earthquake magnitude, earthquake source to site distance, average shear-wave velocity, and faulting mechanisms are used as predictive parameters. The performances of developed hybrid models (PSO-ANFIS-PSO and GA-ANFIS-GA) are compared with the ANFIS model and also the most common soft computing approaches available in the literature. According to the obtained results, three developed models can be effectively used to predict the PGA parameter, but the comparison of models shows that the PSO-ANFIS–PSO model provides better results.
A. Kaveh, S. M. Hamze-Ziabari, T. Bakhshpoori,
Volume 8, Issue 2 (8-2018)
Abstract
In the present study, the multivariate adaptive regression splines (MARS) technique is employed to estimate the drying shrinkage of concrete. To this purpose, a very big database (RILEM Data Bank) from different experimental studies is used. Several effective parameters such as the age of onset of shrinkage measurement, age at start of drying, the ratio of the volume of the sample on its drying surface, relative humidity, cement content, the ratio between water and cement contents, the ratio of sand on total aggregate, average compressive strength at 28 days, and modulus of elasticity at 28 days are included in the developing process of MARS model. The performance of MARS model is compared with several codes of practice including ACI, B3, CEB MC90-99, and GL2000. The results confirmed the superior capability of developed MARS model over existing design codes. Furthermore, the robustness of the developed model is also verified through sensitivity and parametric analyses.
