relation: https://khub.utp.edu.my/scholars/13756/
title: Experimental studies of fpso responses with validation by numerical and artificial neural network prediction
creator: Azizan, N.L.
creator: Irawan, R.
creator: Liew, M.S.
creator: Al-Yacouby, A.M.
creator: Danyaro, K.U.
description: There will be a force on the floating systems after applied environmental load which has an important effect on the performance and safety of the structure. Therefore, the research on orientation of the structure and wave impact has a practical significance. Experimental and numerical simulation becomes valuable in predicting the performance during the system operation. Hence, in this article, a study on the effect of FPSO response by changing the orientation of FPSO has been presented by conducting experiments in the UTP wave basin subjected to regular wave condition. The results are used to be validated with numerical models using a commercial software AQWA by the 3D frequency domain theory and presented in terms of Response Amplitude Operators (RAO) of six degrees of freedom. To accurately consider the effect of response, artificial neural network (ANN) is adopted to predict the FPSO behaviour under different orientations and validate the results. ANN can provide meaningful solutions and can process information in extremely rapid mode ensuring high accuracy of prediction, especially for long response in time histories. Results show that three methods were achieved to generalize the responses. © Springer Nature Singapore Pte Ltd 2020.
publisher: Springer Science and Business Media Deutschland GmbH
date: 2020
type: Article
type: PeerReviewed
identifier:   Azizan, N.L. and Irawan, R. and Liew, M.S. and Al-Yacouby, A.M. and Danyaro, K.U.  (2020) Experimental studies of fpso responses with validation by numerical and artificial neural network prediction.  Lecture Notes in Mechanical Engineering.  pp. 469-482.  ISSN 21954356     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85091294092&doi=10.1007%2f978-981-15-5753-8_43&partnerID=40&md5=c03e3d387fa8f7ab618caca2c425139d
relation: 10.1007/978-981-15-5753-8₄₃
identifier: 10.1007/978-981-15-5753-8₄₃