Determination of the static pressure loads on a marine composite panel from strain measurements utilising artificial neural networks

This source preferred by Mehran Koohgilani, Siamak Noroozi and Philip Sewell

Authors: Ramazani, M., Noroozi, S., Koohgilani, M., Cripps, B. and Sewell, P.

Journal: Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment

Volume: 227

Issue: 1

Pages: 12-21

ISSN: 1475-0902

DOI: 10.1177/1475090212449231

Current practices to predict the loads on the hull of small high-speed craft in a seaway rely either on oversimplified and semi-empirical methods or the use of numerical simulation techniques. These methods are often conservative, leading to a craft that is heavier and slower than it could be otherwise. Therefore, a novel technique is required to overcome these limitations. This paper reports on research undertaken to develop an inverse problem approach utilising an Artificial Neural Network (ANN) for real-time load monitoring of marine structures providing a tool for study of static and dynamic characteristics of the hull. The suitability and performance of utilising an ANN for quantifying the external load applied to a marine structure is presented. The structure under consideration was a Glass Reinforced Fibre Polymer (GRFP) marine composite marine panel. It was found that the ANN was able to accurately predict normal loads applied to up to 12 locations on the panel. It is concluded that the inverse problem approach can be used to predict applied loads on the marine structure in real-time. Therefore, an accurate load history for the structure and/or the structure’s health can be determined/monitored in-service without requiring knowledge of its material properties or geometry.

This data was imported from Web of Science (Lite):

Authors: Ramazani, M.R., Noroozi, S., Koohgilani, M., Cripps, B. and Sewell, P.

Journal: PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART M-JOURNAL OF ENGINEERING FOR THE MARITIME ENVIRONMENT

Volume: 227

Issue: M1

Pages: 12-21

ISSN: 1475-0902

DOI: 10.1177/1475090212449231

The data on this page was last updated at 04:54 on April 18, 2019.