Support vector regression based metamodeling for structural reliability analysis

• Published in: Probabilistic engineering mechanics Vol. 55; pp. 78 - 89
• Main Authors: Roy, Atin, Manna, Ramkrishna, Chakraborty, Subrata
• Format: Journal Article
• Language: English
• Published: Barking Elsevier Ltd 01.01.2019; Elsevier Science Ltd
• Subjects: Algorithms; Artificial neural networks; Computer simulation; Empirical analysis; Finite element analysis; Finite element method; Kernel functions; Kriging; Mathematical models; Metamodel; Metamodels; Monte Carlo simulation; Neural networks; Optimization; Parameter optimization; Parameters; Polynomials; Regression analysis; Regularization; Reliability; Reliability analysis; Reliability engineering; Response surface methodology; Statistical analysis; Structural reliability; Support vector machines; Support vector regression; Support vector regression; Reliability analysis; Parameter optimization; Metamodel

Various metamodeling approaches e.g. polynomial response surface method artificial neural network, Kriging method etc. have been emerged as an effective alternative for solving computationally challenging complex reliability analysis problems involving finite element response analysis. However, such...