Neural Network Model Selection for Dynamic Strain Measurement using Frequency-Domain Parameters of Fiber Optic Sensor

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

Second Generation Coconut Biodiesel: the Best Biodiesel Alternative to Diesel as a Fuel in a Compression Ignition Engine

The numerous experimental works carried out in the past on biodiesels have not come up with any conclusion on the best biodiesel that can replace diesel. Hence, the present work focuses on understanding the technical fea...

EFFECT OF CUTTING SPEED ON GENERATION OF HEAT AT WORK-TOOL INTERFACE OF COPPER BASED SILVER AND BRASS ALLOYS

Copper and its alloys are extensively used in various electrical and other industrial applications, due to its high thermal and electrical conductivity. The machinability of copper depends on its alloying elements and it...

Dynamic Stability of Plates Resting on Elastic Foundation

An accurate closed form solution to predict the dynamic stability behaviour of a square plate resting on an elastic foundation subjected to edge periodic loads, has been obtained. The Energy method is applied to solve th...

Peri-Urban Areas: Sustainability Dimension

Peri-urban areas are defined as the areas that surround our metropolitan areas and cities - neither urban nor rural in the conventional sense. They are the fastest growing regions, globally. This paper comprises of vario...

Heat and Mass Transfer Modelling in Lyophilization Process for an Apple Slices

The aim of this paper is to develop a mathematical model, which simulates the lyophilization process for an apple slices. In the lyophilization process, the moisture content in the slices is removed with the help of a fr...

Download PDF file
  • EP ID EP671654
  • DOI 10.24247/ijmperdoct201927
  • Views 92
  • Downloads 0

How To Cite

A. S. Wali, Amit Tyagi (2019). Neural Network Model Selection for Dynamic Strain Measurement using Frequency-Domain Parameters of Fiber Optic Sensor. International Journal of Mechanical and Production Engineering Research and Development (IJMPERD ), 9(5), 319-332. https://europub.co.uk/articles/-A-671654