Details
| Original language | English |
|---|---|
| Pages (from-to) | 368-391 |
| Number of pages | 24 |
| Journal | Mechanical Systems and Signal Processing |
| Volume | 126 |
| Early online date | 23 Feb 2019 |
| Publication status | Published - 1 Jul 2019 |
Abstract
For engineering applications, the dynamic system responses can be significantly affected by uncertainties in the system parameters including material and geometric properties as well as by uncertainties in the excitations. The reliability of dynamic systems is widely evaluated based on the first-passage theory. To improve the computational efficiency, surrogate models are widely used to approximate the relationship between the system inputs and outputs. In this paper, a new machine learning based metamodel, namely the extended support vector regression (X-SVR), is proposed for the reliability analysis of dynamic systems via utilizing the first-passage theory. Furthermore, the capability of X-SVR is enhanced by a new kernel function developed from the vectorized Gegenbauer polynomial, especially for solving complex engineering problems. Through the proposed approach, the relationship between the extremum of the dynamic responses and the input uncertain parameters is approximated by training the X-SVR model such that the probability of failure can be efficiently predicted without using other computational tools for numerical analysis, such as the finite element analysis (FEM). The feasibility and performance of the proposed surrogate model in dynamic reliability analysis is investigated by comparing it with the conventional ε-insensitive support vector regression (ε-SVR) with Gaussian kernel and Monte Carlo simulation (MSC). Four numerical examples are adopted to evidently demonstrate the practicability and efficiency of the proposed X-SVR method.
Keywords
- Dynamic analysis, Extended support vector regression, Generalized Gegenbauer kernel, Reliability analysis, Surrogate model
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Signal Processing
- Engineering(all)
- Civil and Structural Engineering
- Engineering(all)
- Aerospace Engineering
- Engineering(all)
- Mechanical Engineering
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Mechanical Systems and Signal Processing, Vol. 126, 01.07.2019, p. 368-391.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Dynamic reliability analysis using the extended support vector regression (X-SVR)
AU - Feng, Jinwen
AU - Liu, Lei
AU - Wu, Di
AU - Li, Guoyin
AU - Beer, Michael
AU - Gao, Wei
N1 - Funding Information: The work presented in this paper has been supported by Australian Research Council projects DP160103919 and IH150100006.
PY - 2019/7/1
Y1 - 2019/7/1
N2 - For engineering applications, the dynamic system responses can be significantly affected by uncertainties in the system parameters including material and geometric properties as well as by uncertainties in the excitations. The reliability of dynamic systems is widely evaluated based on the first-passage theory. To improve the computational efficiency, surrogate models are widely used to approximate the relationship between the system inputs and outputs. In this paper, a new machine learning based metamodel, namely the extended support vector regression (X-SVR), is proposed for the reliability analysis of dynamic systems via utilizing the first-passage theory. Furthermore, the capability of X-SVR is enhanced by a new kernel function developed from the vectorized Gegenbauer polynomial, especially for solving complex engineering problems. Through the proposed approach, the relationship between the extremum of the dynamic responses and the input uncertain parameters is approximated by training the X-SVR model such that the probability of failure can be efficiently predicted without using other computational tools for numerical analysis, such as the finite element analysis (FEM). The feasibility and performance of the proposed surrogate model in dynamic reliability analysis is investigated by comparing it with the conventional ε-insensitive support vector regression (ε-SVR) with Gaussian kernel and Monte Carlo simulation (MSC). Four numerical examples are adopted to evidently demonstrate the practicability and efficiency of the proposed X-SVR method.
AB - For engineering applications, the dynamic system responses can be significantly affected by uncertainties in the system parameters including material and geometric properties as well as by uncertainties in the excitations. The reliability of dynamic systems is widely evaluated based on the first-passage theory. To improve the computational efficiency, surrogate models are widely used to approximate the relationship between the system inputs and outputs. In this paper, a new machine learning based metamodel, namely the extended support vector regression (X-SVR), is proposed for the reliability analysis of dynamic systems via utilizing the first-passage theory. Furthermore, the capability of X-SVR is enhanced by a new kernel function developed from the vectorized Gegenbauer polynomial, especially for solving complex engineering problems. Through the proposed approach, the relationship between the extremum of the dynamic responses and the input uncertain parameters is approximated by training the X-SVR model such that the probability of failure can be efficiently predicted without using other computational tools for numerical analysis, such as the finite element analysis (FEM). The feasibility and performance of the proposed surrogate model in dynamic reliability analysis is investigated by comparing it with the conventional ε-insensitive support vector regression (ε-SVR) with Gaussian kernel and Monte Carlo simulation (MSC). Four numerical examples are adopted to evidently demonstrate the practicability and efficiency of the proposed X-SVR method.
KW - Dynamic analysis
KW - Extended support vector regression
KW - Generalized Gegenbauer kernel
KW - Reliability analysis
KW - Surrogate model
UR - http://www.scopus.com/inward/record.url?scp=85061910019&partnerID=8YFLogxK
U2 - 10.1016/j.ymssp.2019.02.027
DO - 10.1016/j.ymssp.2019.02.027
M3 - Article
AN - SCOPUS:85061910019
VL - 126
SP - 368
EP - 391
JO - Mechanical Systems and Signal Processing
JF - Mechanical Systems and Signal Processing
SN - 0888-3270
ER -