Modelling of a flexible plate using RLS with variable and directional forgetting factor

The present study considers the application of recursive least squares (RLS) method with variable forgetting factor (VF) and directional forgetting factor (DF) in dynamic modelling of a flexible plate structure. Recursive least squares with fixed forgetting factor is used to update parameter changes suitable for stationary environments. However for dynamic environments, VF is needed to include fast tracking capability. The performance of the algorithm is compared with that of standard RLS using operations based on one-step-ahead prediction. The performance of each algorithm is assessed in terms of mean square of output error and frequency domain response of the model in characterizing the plate system. Correlation tests are also carried out to validate the model. Simulation results show that the new algorithm can outperform the fixed forgetting factor algorithm in parametric modelling of the flexible structure.