Aircraft wing structural damage localization research based on RBF neural network

Based on mode shape, a new parameter was put forward—mode shape curvature ratio, for detecting structure damages. And it was also the input vector of the RBF neural network. Then through finite element analysis and calculating, the training and forecasting samples were got for the network. The trained neural network can identify the damage location and degree of the frame structure. It proved that this method is simple and valid.

Download Full-text

Structural Damage Localization Based on AR Model and BP Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.94-96.1211 ◽

2011 ◽

Vol 94-96 ◽

pp. 1211-1215

Author(s):

Yan Song Diao ◽

Fei Yu ◽

Dong Mei Meng

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Structural Damage ◽

Ar Model ◽

Model Parameters ◽

Damage Localization ◽

Modal Parameter ◽

Damage Location ◽

Simulation And Experiment ◽

Damage Characteristic

When the AR model is used to identify the structural damage, one problem is often met, that is the method can only make a decision whether the structure is damaged, however, the damage location can not be identified exactly. A structural damage localization method based on AR model in combination with BP neural network is proposed in this paper. The AR time series models are used to describe the acceleration responses. The changes of the first 3-order AR model parameters are extracted and composed as damage characteristic vectors which are put into BP neural network to identify the damage location. The effectiveness of the method is validated by the results of numerical simulation and experiment for a four-layer offshore platform. Only the acceleration responses can be used adequately to localize the structural damage, without the usage of modal parameter and excitation force. Thus the dependence on the modal parameter and excitation can be avoided in this method.

Download Full-text

Study on the structural damage identification method with combined parameters based on RBF neural network

Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693) ◽

10.1109/icmlc.2003.1260134 ◽

2004 ◽

Author(s):

Yu Yang ◽

Jun-Sheng Cheng ◽

Ge Ding ◽

Dan Tian

Keyword(s):

Neural Network ◽

Structural Damage ◽

Damage Identification ◽

Rbf Neural Network ◽

Identification Method ◽

Structural Damage Identification ◽

Combined Parameters

Download Full-text

Damage Localization of Cable-Supported Bridges Using Modal Frequency Data and Probabilistic Neural Network

Mathematical Problems in Engineering ◽

10.1155/2014/837963 ◽

2014 ◽

Vol 2014 ◽

pp. 1-10 ◽

Cited By ~ 13

Author(s):

X. T. Zhou ◽

Y. Q. Ni ◽

F. L. Zhang

Keyword(s):

Neural Network ◽

Structural Damage ◽

Probabilistic Neural Network ◽

Random Noise ◽

Measurement Data ◽

Frequency Change ◽

Damage Localization ◽

Pattern Class ◽

Modal Frequency ◽

Training Samples

This paper presents an investigation on using the probabilistic neural network (PNN) for damage localization in the suspension Tsing Ma Bridge (TMB) and the cable-stayed Ting Kau Bridge (TKB) from simulated noisy modal data. Because the PNN approach describes measurement data in a Bayesian probabilistic framework, it is promising for structural damage detection in noisy conditions. For locating damage on the TMB deck, the main span of the TMB is divided into a number of segments, and damage to the deck members in a segment is classified as one pattern class. The characteristic ensembles (training samples) for each pattern class are obtained by computing the modal frequency change ratios from a 3D finite element model (FEM) when incurring damage at different members of the same segment and then corrupting the analytical results with random noise. The testing samples for damage localization are obtained in a similar way except that damage is generated at locations different from the training samples. For damage region/type identification of the TKB, a series of pattern classes are defined to depict different scenarios with damage occurring at different portions/components. Research efforts have been focused on evaluating the influence of measurement noise level on the identification accuracy.

Download Full-text