Comparison of vibration response prediction on the main deck of a catamaran using experimental, numerical and correlated mode shapes

Abstract

This work analyses the influence of three types of modal matrices on the prediction of vibration response (virtual sensing), at unmeasured degree of freedoms (DOFs), on a catamaran’s main deck: (1) uncorrelated finite element (FE), (2) correlated FE and (3) experimental modal matrices.A multi-objective genetic algorithm (MOGA) framework was developed to handle the optimization and prediction processes. This framework introduces a new metric called Time–Frequency-Error Response Assurance Criteria (TFERAC) to assess the prediction quality. This metric also allows estimating the best set of modal acceleration vectors, which is a critical step in the virtual sensing process.As a case study, only 06 accelerometers and 13 vibration modes (within each modal matrix) were used in the virtual sensing. The MOGA framework’s performance was evaluated using a variance analysis test (ANOVA) between measured and predicted response signals.Results showed that: (1) any one of the modal matrices could be used successfully for virtual sensing on the main deck, that is, there is no need to use correlated FE or experimental modal matrices; (2) the newly proposed metric TFERAC leads to smaller errors in the prediction of both vibration time series and vibration spectra;(3) it is possible to perform a virtual sensing on a ship’s main deck using a limited number of sensors and a numerical modal matrix without being correlated with experimental data.