Generation of Near‐Field Artificial Ground Motions Compatible with Median‐Predicted Spectra Using PSO‐Based Neural Network and Wavelet Analysis

Abstract

The principal purpose of this article is to present a novel method based on particle swarm optimization (PSO) and wavelet packet transform (WPT) techniques and multilayer feed‐forward (MLFF) neural networks, in order to generate spectrum‐compatible near‐field artificial earthquake accelerograms. PSO is employed to optimize the weight values of the networks. Moreover, to improve the training efficiency principal component analysis (PCA) is used, as a reduction technique. The proposed PSO‐based MLFF (PSOBMLFF) neural network develops an inverse mapping from compacted and reduced spectrum coefficients into metamorphosed accelerogram wavelet packet coefficients. In this research, to produce compatible synthetic long‐period near‐field ground motions with median predicted spectra, the attenuation of peak ground velocity (PGV) with the close horizontal distance (R), moment magnitude (M), and time‐average shear‐wave velocity from the surface to 30 m (Vs30) has been developed using nonlinear regression analysis.

Multifractal characteristic analysis of near-fault earthquake ground motions

“…Thus, they have drawn extensive attention in the community of earthquake engineering [1][2][3][4][5][6][7]. In fact, the effects of dynamic forward directivity and static fling-step in earthquake fault result in near-fault ground motions containing distinct longperiod pulses, especially velocity pulses [43][44][45].…”

“…Characteristics of near-fault earthquake ground motions and their damage potential to the civil infrastructures have drawn intensive attention among the academic and engineering community in the recent two decades [1][2][3][4][5][6][7]. Especially, the velocity pulses of near-fault ground motions with the rupture forward directivity and fling-step effects usually result in severe damage to medium-long period structures.…”

A hybrid linear text segmentation algorithm using hierarchical agglomerative clustering and discrete particle swarm optimization

“…3.2) Compute the similarities between adjacent clusters by Eq. (11) and merge the nearest pair of adjacent clusters.…”

“…Particle Swarm Optimization (PSO) [11,18,24,27,30] is one of the evolutional algorithms [1,11,18,24,26,27,30,31], which is a swarm intelligence technique and has been successfully applied in various areas such as document clustering [35] and text mining [23]. In PSO, each particle is an individual, and the swarm is composed of particles.…”

“…It not only provides linear time computational complexity, but also provides segmentation accuracy comparable with several well-known linear text segmentation algorithms. DPSO [19], the discrete version of Particle Swarm Optimization (PSO) [11,18,24,27,30], is a stochastic and population based evolutionary algorithm that is used to find the optimal solution by seeding the solution of TSHAC.…”