Neural Network Model Selection for Dynamic Strain Measurement using Frequency-Domain Parameters of Fiber Optic Sensor
Journal Title: International Journal of Mechanical and Production Engineering Research and Development (IJMPERD ) - Year 2019, Vol 9, Issue 5
Abstract
The present study is aimed to develop a smart strain prediction model using fibre optic sensors and neural network. Frequency domain optical parameters are obtained experimentally using a cantilever beam structure, under dynamic loading conditions. Four variations with external damage are used to study strain variations on healthy, single damage and multiple damage beam structures. The strain values were correlated to the set of phase difference, change in real part and amplitude by using feed-forward back propagation neural network approach. The strain values using optical parameters were verified with analytical strain measurement. As the signals always get affected due to the presence of noise, this drawback is eliminated using a well trained neural network model. The neural network model provides a better and advanced methodology for strain prediction compared to the conventional analytical solution.
Authors and Affiliations
A. S. Wali, Amit Tyagi
Keywords
Related Articles
- EP ID EP671654
- DOI 10.24247/ijmperdoct201927
- Views 81
- Downloads 0
Wear Analysis by Taguchi Technique of Al6061 Based Hybrid Composite Reinforced with Sic and Al2o3
In this paper, wear characteristics of hybrid composite of Al6061 was studied. Hybrid composite was reinforced with silicon carbide (SiC) with varying (3%, 6%, 9%) weight % and keeping the alumina (Al2O3) with constant (...
A Novel Visual SISO and MIMO Computer Interface for Process Production System
Computer based automation systems have found a wide range of applications in manufacturing and processing industries. To interface computer and control system, various standard industrial interfaces were used. Because of...
Buckling of Cones with Imperfect Length Subjected to Axial Compression
The paper considers the effect of imperfect length on the buckling behavior of mild steel truncated cone subjected to axial compression. The contact interaction problem between the rigid plate and the cone was successful...
CHARACTERIZATION OF ADDITIVE MANUFACTURED ABS AND NATURAL ABS SPECIMENS
Additive Manufacturing (AM) is a Rapid Prototyping technique. It is used for producing any real complex parts from the desired 3D CAD models. It can also manufacture prototypes. Additive Manufacturing can utilize raw mat...
Dynamic Impact Analysis on ATV Upright
Uprights play a vital role carrying the complete wheel assembly with it and attached to vehicle suspension system. The knuckle has to design in order to sustain all the loads acting on the vehicle during the course of dy...