Application of convolutional neural network in random structural damage identification

In recent years, there were been increasing researches focusing on the application of artificial neural networks in structural damage identification. Most of them perform well with numerical examples under error-free conditions, but become worse when the experimental data are polluted with measurement noise. In this paper, a dynamic approach based on PNN for damage identification of composite materials was proposed. By using wavelet series, the features of signals were extracted and input to PNN for training the network and identifying the damages. A performance comparison between the PNN and BPNN for structural damage identification was carried out. The results show that the proposed method can more exactly identify the faults than the BP neural network.

Download Full-text

A REVIEW PAPER ON STRUCTURAL DAMAGE IDENTIFICATION OF CANTILEVER BEAM BY USING VIBRATION TECHNIQUE, FINITE ELEMENT ANALYSIS & ARTIFICIAL NEURAL NETWORK

International Journal of Research -GRANTHAALAYAH ◽

10.29121/granthaalayah.v3.i12.2015.2896 ◽

2015 ◽

Vol 3 (12) ◽

pp. 125-128

Author(s):

Aakanksha MohanraoGarud ◽

V. G. Bhamre

Keyword(s):

Neural Network ◽

Finite Element Analysis ◽

Artificial Neural Network ◽

Structural Damage ◽

Review Paper ◽

Damage Identification ◽

Frequency Measurement ◽

Element Analysis ◽

Structural Damage Identification ◽

Artificial Neural

In this review paper structural damage identification work in cantilever beam is done by using the Artificial Neural Network as diagnostic parameter. The study is based on the concept that natural frequency is inversely proportional to the mass of the structure. Thus to regulate the proper condition of structure, periodical frequency measurement is necessary. But in dynamic conditions and in complicated structures frequency measurement is difficult, for the same we reviewed various papers to identify the structural damage using various methods. The factors which affects on the damage of structural parts like crack depth, crack location etc. is also discussed in this work. Natural frequency is measured with the help of fast fourier transform by various authors and artificial neural network is also used for identification of the damage in many papers. So in this review work we studied methods of structural damage identification such as vibrations, finite element analysis and artificial neural network.

Download Full-text

Damage Severity Assessment Using Modified BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.179-180.1016 ◽

2011 ◽

Vol 179-180 ◽

pp. 1016-1020

Author(s):

Xiao Ma Dong ◽

Zhong Hui Wang

Keyword(s):

Neural Network ◽

Composite Material ◽

Bp Neural Network ◽

Structural Damage ◽

Simulation Experiment ◽

Damage Identification ◽

Severity Assessment ◽

Improved Method ◽

Modal Frequency ◽

Structural Damage Identification

Damage severity identification is an important content among structural damage identification. In order to avoid the disadvantages of conventional BPNN, a modified BP neural network was proposed to identify structural damage severity in this paper. The modified BPNN was trained by using structural modal frequency qua BPNN input, and then used to forecast structural damage severity. Finally, the results of simulation experiment of composite material cantilever girder show that the improved method is very effective for damage severity identification and possess great applied foreground.

Download Full-text