DAMAGE DIAGNOSIS IN BEAM-LIKE STRUCTURES BY ARTIFICIAL NEURAL NETWORKS

Journal of Civil Engineering and Management - Tập 21 Số 5 - Trang 591-604
Kamil Aydin1, Özgür Kişi2
1Department of Civil Engineering, Faculty of Engineering, Erciyes University, 38039 Kayseri, Turkey
2Canik Basari University

Tóm tắt

Applicability of artificial neural networks is examined in determining the natural frequencies of intact beams and crack parameters of damaged beams. Multi-layer perceptron (MLP) and radial basis neural networks (RBNN) are utilized for training and validation of input data. In the first part of the study, the first four frequencies of free vibration are predicted based on beam properties by the networks. Showing the effectiveness of the neural networks in predicting the vibrational frequencies, the second part of the study is carried out. At this stage of the inverse problem, the frequencies and mode shape rotation deviations in addition to beam properties are used as input to the networks to determine the crack parameters. Different hidden nodes, epochs and spread values are tried to find the optimal neural networks that give the lowest error estimates. In both parts of the study, the RBNN model performs better. The robustness of the network models in the presence of noise is also shown. It is shown that the optimal MLP network predicts the crack parameters slightly better in the presence of noise. As a conclusion, the trained RBNN model can be used in health monitoring of beam-like structures as a crack identification algorithm.

Từ khóa


Tài liệu tham khảo

10.1006/jsvi.1999.2295

10.1006/jsvi.2001.3989

10.1016/j.engstruct.2007.01.013

Broomhead D., 1988, Complex Systems, 2, 321

10.1177/1475921704047500

10.1623/hysj.48.3.349.45288

10.12989/sem.2004.18.3.303

10.1016/0013-7944(94)00175-8

10.1177/1475921710365419

10.1006/jsvi.1999.2179

10.1016/0022-5096(82)90004-7

10.1109/72.329697

Haykin, S. 1998.Neural networks:a comprehensive foundation. Upper Saddle River: Prentice Hall. 842 p.

Hoit, M. I. 1994.Computer assisted structural analysis and modeling. Upper Saddle River: Prentice Hall. 440 p.

10.1061/(ASCE)0887-3801(1994)8:2(201)

10.1016/j.jsv.2007.07.092

10.1088/0964-1726/10/3/307

10.1623/hysj.49.6.1025.55720

10.1016/j.compfluid.2007.11.002

Kocabas F., 2010, The Kuwait Journal of Science and Engineering, 37, 21

10.1016/j.advengsoft.2009.12.021

10.1016/S0306-4549(03)00099-9

10.1016/j.jsv.2004.01.003

10.1006/jsvi.1999.2856

10.1006/jsvi.2001.4034

10.1007/11427469_95

10.1016/S0045-7825(02)00221-9

10.1137/0111030

10.1006/mssp.1998.1218

10.1006/jsvi.1996.0856

10.1016/S0045-7949(96)00120-4

10.1006/jsvi.1994.1002

10.1016/0022-460X(91)90595-B

10.1126/science.247.4945.978

10.1115/1.1303121

10.1016/j.engstruct.2009.04.007

Saeed R. A., 2011, Journal of Computing, 3, 113

10.1016/j.engstruct.2003.08.001

10.4028/www.scientific.net/KEM.245-246.69

10.1061/(ASCE)0733-9399(2000)126:12(1216)

10.1061/(ASCE)0733-9399(2000)126:6(656)

10.1061/(ASCE)0733-9399(2002)128:5(521)

10.1088/0964-1726/13/4/029

10.1016/j.jsv.2003.07.040

10.1115/1.1857918

10.1016/0045-7949(92)90132-J

10.1016/j.ymssp.2006.10.002

10.1016/S0045-7949(99)00199-6

10.1006/mssp.2002.1547

Thông tin
Thông tin xuất bản

Journal of Civil Engineering and Management

Tập 21 Số 5

591-604

Thông tin tác giả