Vessel Condition Monitorization Through Satellite Using Principal Component Analysis

Abstract

Abstract - Offshore telecommunications are possible in virtually all parts of the world via satellite. Satellite communications are increasing the bandwidth and lowering the cost, but are still far from levels that are in earth. Principal components analysis (PCA) is a statistical technique that has found application in fields such as biometrics or compression of images, being a common tool for the search of pattern of multidimensional data sets. The hypothesis of this study was the possibility of using the PCA theory to compress, with sufficient accuracy, the large amount of data that are collected on board, and then send them all via satellite, in a cheaper and faster way than traditionally. The materials used were 44 samples of 182 different signals, obtained from 19 different equipment on board the LNG vessel “Castillo de Villalba”. With these data the PCA algorithm was applied, using a computer program developed by the authors, generating new data packets to send by satellite. Different strategies were used in order to ensure that the correlation coefficient was equal or greater than 0.95 in the comparison between original data and reconstructed data onshore. Results obtained by grouping the 182 signals showed 46.9% reduction in data sent via satellite, with a mean r = 0.95 ± 0.08.
This strategy is appropriate for decision making about tele-diagnosis and maintenance of the ship using ground equipment. Consequently, significant savings are achieved in telecommunication costs and telecommunication times.