A Wavelet Support Vector Machine‐Based Neural Network Metamodel for Structural Reliability Assessment

Computer-Aided Civil and Infrastructure Engineering - Tập 32 Số 4 - Trang 344-357 - 2017
Hongzhe Dai1, Zhenggang Cao1
1School of Civil Engineering, Harbin Institute of Technology, Harbin, China and Key Lab of Structures Dynamic Behavior and Control (Harbin Institute of Technology), Ministry of Education Harbin 150090 China

Tóm tắt

Abstract

Wavelet neural network (WNN) has been widely used in the field of civil engineering. However, WNN can only effectively handle problems of small dimensions as the computational cost for constructing wavelets of large dimensions is prohibitive. To expand the application of WNN to higher dimensions, this article develops a new wavelet support vector machine (SVM)‐based neural network metamodel for reliability analysis. The method first develops an autocorrelation wavelet kernel SVM and then uses a set of wavelet SVMs with different resolution as the activation function of WNN. The output of network is obtained through aggregating outputs of different wavelet SVMs. The method takes advantage of the excellent capacities of SVM to handle high‐dimensional problems and of the attractive properties of wavelet to represent complex functions. Four examples are given to demonstrate the application and effectiveness of the proposed method.

Từ khóa


Tài liệu tham khảo

10.1111/0885-9507.00219

Adeli H., 1994, Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems

Adeli H., 2009, Intelligent Infrastructure: Neural Networks, Wavelets, and Chaos Theory for Intelligent Transportation Systems and Smart Structures

10.1061/(ASCE)0733-947X(2000)126:6(464)

Adeli H., 2005, Wavelets in Intelligent Transportation Systems

Adeli H., 2009, Wavelet‐Based Vibration Control of Smart Buildings and Bridges

10.1111/0885-9507.00189

10.1016/j.neunet.2013.01.008

10.12989/sem.2009.32.1.071

Bezdek J. C.(1981) Pattern Recognition with Fuzzy Objective Function Algorithms Plenum Press New York.

10.1111/mice.12126

10.1016/j.probengmech.2007.12.022

10.1111/mice.12153

10.1111/mice.12195

10.1111/mice.12121

10.1111/mice.12117

10.1016/j.ress.2012.04.011

10.1111/mice.12086

10.1111/j.1467-8667.2012.00767.x

10.1007/s12206-011-0704-5

10.1016/j.cnsns.2016.06.034

10.1016/j.chaos.2016.12.006

Dai H. Zheng Z.&Wang W.(2017c) Nonlinear system stochastic response determination via fractional equivalent linearization and Karhunen‐Loeve expansion Communications in Nonlinear Science and Numerical Simulation DOI: 10.1016/j.cnsns.2017.01.033.

10.1137/1.9781611970104

10.1016/j.probengmech.2013.02.002

10.1016/j.strusafe.2006.10.003

10.1007/978-1-4612-3094-6

10.1016/j.jsv.2007.10.050

10.1109/TBME.2007.891945

10.1016/S0167-4730(02)00013-9

10.1007/s10916-015-0353-9

10.1016/j.strusafe.2003.05.002

10.1007/978-3-540-40987-8

10.1016/S0045-7825(01)00248-1

10.1061/(ASCE)0733-9445(2003)129:8(1141)

10.1016/j.probengmech.2009.05.006

10.1111/j.1467-8667.2005.00399.x

10.1002/nme.1964

10.1002/nme.2195

10.1061/(ASCE)0733-947X(2002)128:1(21)

10.1109/72.471353

10.1016/j.compstruc.2010.08.007

10.1142/S0129065707000890

10.1111/j.1467-8667.2009.00595.x

10.1016/S0045-7949(02)00064-0

10.1088/0964-1726/24/12/125040

10.1061/(ASCE)CO.1943-7862.0001047

10.1109/78.258102

10.1016/S0893-6080(98)00032-X

10.1111/mice.12142

10.1109/TSMCA.2012.2224338

Vapnik V. N., 2000, The Nature of Statistic Learning Theory, 10.1007/978-1-4757-3264-1

10.1111/mice.12088

10.1016/j.eswa.2011.05.020

10.1109/78.388860

10.1109/72.557660

10.1109/72.165591