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

Abstract

One of the first steps in marine structural design is to calculate the wave-induced loads and load combinations. In contrast with both the hydrostatic loads and the self-weight loads which can be evaluated with a high degree of confidence, it is more difficult to measure the in-service hydrodynamic loads generated by sea waves. Direct pressure load measurement techniques can currently provide only data at finite locations while classical analytical techniques require knowledge of all the parameters that influence the load and that each parameter is studied independently. Therefore, a novel technique is required to overcome these limitations by providing a method of measuring the pressure load over large areas with relatively few sensors and minimal data collection. This paper reports research undertaken to develop an inverse problem approach utilising an artificial neural network for measurement of the pressure loads experienced by marine structures. The suitability and performance of utilising an artificial neural network for quantifying the pressure load applied to a marine structure is presented. It was found that the artificial neural network was able to estimate accurately the pressure loads applied to up to 12 locations on the structure. It is concluded that the inverse problem approach can be used to estimate the applied loads on the marine structure in real time from strain measurements.

Keywords

Composite marine artificial intelligence artificial neural network structural analysis load

Get full access to this article

View all access options for this article.

References

Phelps

. Determination of wave loads for ship structural analysis. Report DSTO-RR-0116, Aeronautical and Maritime Research Laboratory, Defence Science and Technology Organisation, Melbourne, Victoria, Australia, 1997.

Koelbel

Jr . Comments on the structural design of high speed craft. Mar Technol 1995; 32(2): 77–100.

G-D

Duan

W-Y

. Review of prediction techniques on hydrodynamic impact of ships. Mar Sci Applic 2009; 8: 204–210.

Adamchak

. An approximate method for estimating the collapse of a ship’s hull in preliminary design. In: SSC-SNAME structural symposium, Arlington, VA, USA, 15–16 October 1984, pp. 37–61.

Baldwin

Niemczuk

Kiddy

. Structural testing of navy vessels using bragg gratings and a prototype digital spatial wavelength domain multiplexing (DSWDM) system. Nav Engrs J 2002; 114(1): 63–70.

Sikora

Dinsenbacher

Beach

. A method for estimating lifetime loads and fatigue lives for swath and conventional monohull ships. Nav Engrs J 1983; 95(3): 63–85.

Faltinsen

. Challenges in hydrodynamics of ships and ocean structures. J Nav Archit Shipbuilding Ind 2007; 58(3): 268–277.

Cao

Sugiyama

Mitsui

. Application of artificial neural networks to load identification. Comput Structs 1998; 69: 63–67.

Mamdani

Assilian

. An experiment in linguistic synthesis with a fuzzy logic controller. J Man–Mach Stud 1975; 7(1): 1–13.

10.

Rao

. C++ neural networks and fuzzy logic. New York: M & T Books, 1995.

11.

Ziemianski

Harpula

. The use of neural networks for damage detection in eight storey frames. In: 5th international conference on engineering applications of neural networks, Warsaw, Poland, 13–15 September 1999, pp. 292–297. Toruń: Wydawnictwa Adam Marszałek.

12.

Amali

Noroozi

Vinney

. The application of combined artificial neural network and finite element method in domain problems. In: 6th international conference on engineering applications of neural networks (EANN 2000), Kingston upon Thames, Surrey, UK, 17–19 July 2000, pp. 1–7. London: Kingston University.

13.

Amali

Noroozi

Vinney

. Predicting interfacial loads between the prosthetic socket and the residual limb for below-knee amputees – a case study. Strain 2006; 42(1): 3–10.

14.

Rosenblatt

. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 1958; 65(6): 386–408.

15.

Shar

Palmieri

. MEKA – a fast, local algorithm for training feed forward neural networks. In: International joint conference on neural networks, Como, Italy, 24–27 July 1990, vol 3, pp. 41–46. New York: IEEE.

16.

Kim

S-Y

Moon

B-Y

Kim

D-E

Shin

. Automation of hull plates classification in ship design system using neural network method. Mech Systems Signal Processing 2006; 20(2): 493–504.

17.

Deng

Tiwar

. An inverse approach for pressure load identification. Int J Impact Engng 2010; 37(7): 865–877.

18.

Kohonen

. An introduction to neural computing. Neural Networks 1998; 1(1): 3–16.

19.

Sewell

Noroozi

Vinney

. Improvements in the accuracy of an inverse problem engine’s output for the prediction of below-knee prosthetic socket interfacial loads. Engng Applic Artif Intell 2010; 23(6): 1000–1011.