Sensor Optimisation for in-Service Load Measurement of a Large Composite Panel under Small Displacement

Abstract:

Current methods to estimate the behaviour of composite structures are based on trial and error or oversimplification. Normally the nonlinearities in these structures are neglected and in order to cover this inadequacy in design of composite structures, an overestimate safety factor is used. These methods are often conservative and leading to the heavier structures. A novel technique employs Artificial Neural Network (ANN) as an inverse problem approach to estimate the pressure loads experienced by marine structures applied on a composite marine panel from the strain measurements. This can be used in real-time to provide an accurate load history for a marine structure without requiring knowledge of the material properties or component geometry. It is proposed that the ANN methodology, with further research and development, could be utilised for the quantification of in-service, transient loads in real-time acting on the craft from the craft’s structural response (strain response to load). However, to fully evaluate this methodology for load monitoring of marine structures further research and development is required such as sensor optimisation. The number of sensors should be minimised to reduce the time to train the system, cost and weight. This study investigates the number of sensors required for accurate load estimation by optimising the method.

References

[1] T. Kukkanen, Wave load predictions for marine structures, Rakenteiden Mekaniikka (J. Structural Mechanics), 43(3) (2010) 150-166.

[2] Y. Bai, Marine structural design, ELSEVIER SCIENCE Ltd, Oxford, (2003).

[3] B.P. Phelps, Determination of Wave Loads for Ship Structural Analysis, DSTO Aeronautical and Maritime Research Laboratory, Australia, (1997).

[4] X. Guo-dong, D. Wen-yang, Review of prediction techniques on hydrodynamic impact of ships, J. Marine Science Application, 8 (2009) 204-210.

[5] A. Ito, S. Mizoguchi, Hydrodynamic pressure acting on a full ship in oblique short waves, J. Soc. Nav. Archit. Jpn., 222 (1994) 125–32 [in Japanese].

[6] I. Watanabe, Practical method for diffraction pressure on a ship running in oblique wave, J. Kansai Soc. Nav. Archit., 221 (1994) 83–9 [in Japanese].

[7] N. Salvesen, E.O. Tuck, O.M. Faltinsen, Ship motions and sea loads, J. Trans. SNAME, 78 (1970) 250–87.

[8] O.M. Faltinsen, Hydrodynamics of high-speed marine vehicles, Cambridge University Press, New York, (2005).

[9] J.J. Jensen, P.T. Pedersen, Wave-induced bending moments in ships: a quadratic theory, J. Trans. Roy. Soc. Nav. Archit. 121(1979) 151–65.

[10] H. Iwashita, A. Ito, T. Okada, M. Ohkusu, M. Takaki, S. Mizoguchi. Wave force acting on a blunt ship with forward speed in oblique sea, J. Soc. Nav. Archit. Jpn., 173 (1993) 195–208 [in Japanese].

[11] H. Yasukawa, A Rankine panel method to calculate unsteady ship hydrodynamic forces, J. Soc. Nav. Archit. Jpn. 168 (1990) 131–40 [in Japanese].

DOI: 10.2534/jjasnaoe1968.1990.168_131

[12] D. Nakos, P. Sclavounos, Ship motions by a three-dimensional Rankine panel method, Proc. of 18th symp. on nav. hydrodynamics, Ann Arbor, (1990) 21–40.

[13] K. Takagi, Calculation of unsteady pressure by Rankine source method, J. Kansai Soc. Nav. Archit., 219 (1993) 47–56 [in Japanese].

[14] O.M. Faltinsen, Challenges in Hydrodynamics of Ships and Ocean Structures, J. Nav. Archit. and Shipbuilding Industry, 58(3) (2007) 268-277.

[15] H. Sun, O.M. Faltinsen, Hydrodynamic forces on a semi-displacement ship at high speed, J. Applied Ocean Research, 34 (2012) 68– 77.

DOI: 10.1016/j.apor.2011.10.001

[16] X. Cao, Y. Sugiyama, Y. Mitsui, Application of artificial neural networks to load identification, J. Computers and Structures, 69 (1998) 63-67.

DOI: 10.1016/s0045-7949(98)00085-6

[17] M.R. Ramazani, S. Noroozi, M. Koohgilani, B. Cripps, P. Sewell, Determination of static pressure loads on a marine composite panel from strain measurements utilising artificial neural networks, submitted to Proceedings of the Institution of Mechanical Engineers, Part M: J. Eng. for the Maritime Environment, (2012).

DOI: 10.1177/1475090212449231

[18] V.B. Rao, H.V. Rao, C++ Neural Networks and Fuzzy Logic, M & T Books, New York, (1995).

[19] L. Ziemianski, G. Harpula, The use of neural networks for damage detection in eight storey frames, Proceedings of the 5th international conference: Engineering applications of neural networks, (1999) 292–297.

[20] R. Amali, S. Noroozi, J. Vinney, The application of combined artificial neural network and finite element method in domain problems, Proceedings of the Sixth International Conference on Engineering Applications of Neural Networks (EANN 2000), (2000).

[21] R. Amali, S. Noroozi, J. Vinney, P. Sewell, S. Andrews, Predicting interfacial loads between the prosthetic socket and the residual limb for below-knee amputees: a case study, J. Strain, 42(1) (2006) 3-10.

DOI: 10.1111/j.1475-1305.2006.00245.x

[22] F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, J. Psychological Review, 65(6) (1958) 386–408.

DOI: 10.1037/h0042519

[23] S. Shar, F. Palmieri, MEKA: a fast, local algorithm for training feed forward neural networks, Proceedings of the International Joint Conference on Neural Networks, (1990) 41–46.

DOI: 10.1109/ijcnn.1990.137822

[22] K. Soo-Young, B.Y. Moon, D.E. Kim, S.C. Shin, Automation of hull plates classification in ship design system using neural network method, J. Mechanical Systems and Signal Processing 20(2) (2006) 493–504.

DOI: 10.1016/j.ymssp.2004.06.008

[23] S. Xu, X. Deng, V. Tiwar, M. A, Sutton, W.L. Fourney, An inverse approach for pressure load identification, Int. J. Impact Engineering, 37(7) (2010) 865–877.

DOI: 10.1016/j.ijimpeng.2009.10.007

[24] R. Amali, S. Noroozi, J. Vinney, P. Sewell, S. Andrews, Improvements in the accuracy of an Inverse Problem Engine's output for the prediction of below-knee prosthetic socket interfacial loads, J. Engineering Applications of Artificial Intelligence, 23(6) (2010).

DOI: 10.1016/j.engappai.2010.02.011