Skip to Main Content
This paper presents an investigation into the performance of system identification using Backpropagation Multi-layer Perceptron Neural Networks algorithm for identification of a flexible plate system. Details of the implementation and the experimental studies are given and analyzed in the paper. The input-output data of the system were first acquired through the experimental studies using National Instrumentation (NI) data acquisition system. A sinusoidal force was then applied to excite the flexible plate and the dynamic response of the system was investigated. A linear parametric model of the system is developed using Recursive Least Square (RLS). Furthermore, a non-parametric model of the system is developed using Multi-layer Perceptron Neural Networks (MLP-NN). Later a comparative performance of the approaches used is presented and discussed. Finally, the validity of the obtained model was investigated using correlation tests.