Structural Damage Detection Based on a Fiber Bragg Grating Sensing Array and a Back Propagation Neural Network: An Experimental Study

The distributed long-gauge fiber Bragg grating sensing technology has been studied and developed in recent years for structural health monitoring of civil engineering structures. Also, the corresponding damage identification method is one of the research hotspots and still needs to be enhanced. In this article, a novel damage detection method based on the distributed long-gauge fiber Bragg grating sensing technique is proposed to detect and localize damages. The method is based on the advanced complete ensemble empirical mode decomposition adaptive noise algorithm. Measured macrostrain responses from the long-gauge fiber Bragg grating sensors are decomposed into intrinsic mode functions, and the quasi-static macrostrains are extrapolated and extracted. A damage indicator is therefore proposed and built based on the quasi-static macrostrain time history. The effectiveness of the proposed damage detection approach was validated by numerical simulations of a cantilever beam. The robustness of the method was further verified by considering the noise pollution contained within the measured macrostrain. Experiments with a practical cantilever steel beam with different damage scenarios were also conducted and studied. Results proved that the proposed method could not only detect but also locate the damages accurately, and therefore has the promising potential for structural damage detection in civil engineering.

Download Full-text

Dynamic learning rate neural network training and composite structural damage detection

AIAA Journal ◽

10.2514/3.13701 ◽

1997 ◽

Vol 35 ◽

pp. 1522-1527

Author(s):

H. Luo ◽

S. Hanagud

Keyword(s):

Neural Network ◽

Damage Detection ◽

Structural Damage ◽

Learning Rate ◽

Neural Network Training ◽

Structural Damage Detection ◽

Dynamic Learning ◽

Network Training

Download Full-text

Identification of Crack Length and Angle at the Center Weld Seam of Offshore Platforms Using a Neural Network Approach

Journal of Marine Science and Engineering ◽

10.3390/jmse8010040 ◽

2020 ◽

Vol 8 (1) ◽

pp. 40 ◽

Cited By ~ 3

Author(s):

Qingxi Yang ◽

Gongbo Li ◽

Weilei Mu ◽

Guijie Liu ◽

Hailiang Sun

Keyword(s):

Neural Network ◽

Crack Length ◽

Structural Damage ◽

Evaluation Method ◽

Weld Seam ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Offshore Platforms ◽

Neural Network Approach ◽

External Interference

The reconstruction algorithm for the probabilistic inspection of damage (RAPID) is aimed at localizing structural damage via the signal difference coefficient (SDC) between the signals of the present and reference conditions. However, tomography is only capable of presenting the approximate location and not the length and angle of defects. Therefore, a new quantitative evaluation method called the multiple back propagation neural network (Multi-BPNN) is proposed in this work. The Multi-BPNN employs SDC values as input variables and outputs the predicted length and angle, with each output node depending on an individual hidden layer. The cracks of different lengths and angles at the center weld seam of offshore platforms are simulated numerically. The SDC values of the simulations and experiments were normalized for each sample to eliminate external interference in the experiments. Then, the normalized simulation data were employed to train the proposed neural network. The results of the simulations and experimental verification indicated that the Multi-BPNN can effectively predict crack length and angle, and has better stability and generalization capacity than the multi-input to multi-output back propagation neural network.

Download Full-text