Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm

Peng Ming Sun; Teng Fei Bao; Chong Shi Gu; Ming Jiang; Tian Wang; Wen Zhong Shi

doi:10.1007/s11431-016-0213-y

Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm

Peng Ming Sun, Teng Fei Bao, Chong Shi Gu, Ming Jiang, Tian Wang, Wen Zhong Shi

Research output: Journal article publication › Journal article › Academic research › peer-review

33 Citations (Scopus)

Abstract

Considering the complex nonlinear relationship between the material parameters of a concrete faced rock-fill dam (CFRD) and its displacements, the harmony search (HS) algorithm is used to optimize the back propagation neural network (BPNN), and the HS-BPNN algorithm is formed and applied for the inversion analysis of the parameters of rock-fill materials. The sensitivity of the parameters in the Duncan and Chang’s E-B model is analyzed using the orthogonal test design. The case study shows that the parameters φ0, K, Rf, and Kbare sensitive to the deformation of the rock-fill dam and the inversion analysis for these parameters is performed by the HS-BPNN algorithm. Compared with the traditional BPNN, the HS-BPNN algorithm exhibits the advantages of high convergence precision, fast convergence rate, and strong stability.

Original language	English
Pages (from-to)	1442-1451
Number of pages	10
Journal	Science China Technological Sciences
Volume	59
Issue number	9
DOIs	https://doi.org/10.1007/s11431-016-0213-y
Publication status	Published - 1 Sept 2016
Externally published	Yes

Keywords

back propagation neural network
concrete faced rock-fill dam
harmony search algorithm
parameter inversion
parameter sensitivity analysis

ASJC Scopus subject areas

General Materials Science
General Engineering

More information

10.1007/s11431-016-0213-y

Cite this

@article{9e5773c00df54b2cb5e0d9d15d429b00,

title = "Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm",

abstract = "Considering the complex nonlinear relationship between the material parameters of a concrete faced rock-fill dam (CFRD) and its displacements, the harmony search (HS) algorithm is used to optimize the back propagation neural network (BPNN), and the HS-BPNN algorithm is formed and applied for the inversion analysis of the parameters of rock-fill materials. The sensitivity of the parameters in the Duncan and Chang{\textquoteright}s E-B model is analyzed using the orthogonal test design. The case study shows that the parameters φ0, K, Rf, and Kbare sensitive to the deformation of the rock-fill dam and the inversion analysis for these parameters is performed by the HS-BPNN algorithm. Compared with the traditional BPNN, the HS-BPNN algorithm exhibits the advantages of high convergence precision, fast convergence rate, and strong stability.",

keywords = "back propagation neural network, concrete faced rock-fill dam, harmony search algorithm, parameter inversion, parameter sensitivity analysis",

author = "Sun, {Peng Ming} and Bao, {Teng Fei} and Gu, {Chong Shi} and Ming Jiang and Tian Wang and Shi, {Wen Zhong}",

year = "2016",

month = sep,

day = "1",

doi = "10.1007/s11431-016-0213-y",

language = "English",

volume = "59",

pages = "1442--1451",

journal = "Science China Technological Sciences",

issn = "1674-7321",

publisher = "Science China Press",

number = "9",

}

TY - JOUR

T1 - Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm

AU - Sun, Peng Ming

AU - Bao, Teng Fei

AU - Gu, Chong Shi

AU - Jiang, Ming

AU - Wang, Tian

AU - Shi, Wen Zhong

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Considering the complex nonlinear relationship between the material parameters of a concrete faced rock-fill dam (CFRD) and its displacements, the harmony search (HS) algorithm is used to optimize the back propagation neural network (BPNN), and the HS-BPNN algorithm is formed and applied for the inversion analysis of the parameters of rock-fill materials. The sensitivity of the parameters in the Duncan and Chang’s E-B model is analyzed using the orthogonal test design. The case study shows that the parameters φ0, K, Rf, and Kbare sensitive to the deformation of the rock-fill dam and the inversion analysis for these parameters is performed by the HS-BPNN algorithm. Compared with the traditional BPNN, the HS-BPNN algorithm exhibits the advantages of high convergence precision, fast convergence rate, and strong stability.

AB - Considering the complex nonlinear relationship between the material parameters of a concrete faced rock-fill dam (CFRD) and its displacements, the harmony search (HS) algorithm is used to optimize the back propagation neural network (BPNN), and the HS-BPNN algorithm is formed and applied for the inversion analysis of the parameters of rock-fill materials. The sensitivity of the parameters in the Duncan and Chang’s E-B model is analyzed using the orthogonal test design. The case study shows that the parameters φ0, K, Rf, and Kbare sensitive to the deformation of the rock-fill dam and the inversion analysis for these parameters is performed by the HS-BPNN algorithm. Compared with the traditional BPNN, the HS-BPNN algorithm exhibits the advantages of high convergence precision, fast convergence rate, and strong stability.

KW - back propagation neural network

KW - concrete faced rock-fill dam

KW - harmony search algorithm

KW - parameter inversion

KW - parameter sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84982291263&partnerID=8YFLogxK

U2 - 10.1007/s11431-016-0213-y

DO - 10.1007/s11431-016-0213-y

M3 - Journal article

SN - 1674-7321

VL - 59

SP - 1442

EP - 1451

JO - Science China Technological Sciences

JF - Science China Technological Sciences

IS - 9

ER -

Parameter sensitivity and inversion analysis of a concrete faced rock-fill dam based on HS-BPNN algorithm

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this