Strain analysis due to vibration can provide insight into structural health. An Extrinsic Fabry-Perot Interferometric
(EFPI) sensor under vibrational strain generates a non-linear modulated output. Advanced signal processing techniques,
to extract important information such as absolute strain, are required to demodulate this non-linear output. Past research
has employed Artificial Neural Networks (ANN) and Fast Fourier Transforms (FFT) to demodulate the EFPI sensor for
limited conditions. These demodulation systems could only handle variations in absolute value of strain and frequency of
actuation during a vibration event. This project uses an ANN approach to extend the demodulation system to include the
variation in the damping coefficient of the actuating vibration, in a near real-time vibration scenario. A computer
simulation provides training and testing data for the theoretical output of the EFPI sensor to demonstrate the approaches.
FFT needed to be performed on a window of the EFPI output data. A small window of observation is obtained, while
maintaining low absolute-strain prediction errors, heuristically. Results are obtained and compared from employing
different ANN architectures including multi-layered feedforward ANN trained using Backpropagation Neural Network
(BPNN), and Generalized Regression Neural Networks (GRNN). A two-layered algorithm fusion system is developed
and tested that yields better results.
Strain level measurement on a periodically actuated and instrumented structure can provide information about the health of that structure. A simple demodulation system employing artificial neural networks (ANNs) is analyzed for an extrinsic Fabry-Pérot interferometric (EFPI) strain sensor. The harmonic content of the nonlinear sensor output for the sinusoidal strain case is used to predict the maximum strain level. Implementations of the demodulation system are demonstrated for both simulated and experimental data using back-propagation neural networks. The simulation uses the theoretical response of the EFPI sensor and the experiment uses an EFPI-instrumented smart composite beam to obtain training and testing data. Excitation is provided by a piezoelectric actuator operating from 50 Hz to 1 kHz. System performance is compared for two-stage and single-stage networks and for differing types of data preprocessing. The ANN systems successfully extract the signal harmonics and predict the peak strain levels. Data preprocessing using principal component analysis produces the best accuracy. The architecture of an EFPI-based health monitoring system is proposed.