Full-scale identification of ice load on ship hull by least square support vector machine method

Abstract For ensuring the structural safety of an icebreaker, the ice load is identified from the strains measured on the frames or plates of the hull along the waterline. The strain sensors are difficult to install, however, at the required locations on the hull because the watertight compartment is cramped. In this situation, the far-field load identification method can be applied to overcome such restriction on the installation location. To determine the nonlinear relationship between ice load and ice-induced strains, the least square support vector machine (LS_SVM) method is adopted. Among the advantages that this method affords for ice load identification are its capacity for small sample learning, global optimization, and strong generalization. In this study, a ship-based ice load measurement system installed on icebreaker XueLong is introduced. The experimental application is performed to verify the feasibility of the LS_SVM procedure and establish a full-scale ice load identification model. With this method, the identified ice load is reasonably verified through comparative analysis and case study. To estimate the ice load through far-field measurements, the predictive ability of the LS_SVM algorithm can further be applied.

[1]  H. Xie,et al.  EISCAM - Digital image acquisition and processing for sea ice parameters from ships , 2009 .

[2]  Stephen F. Ackley,et al.  Thickness distribution of Antarctic sea ice , 2008 .

[3]  Shaojun Li,et al.  Identifying geomechanical parameters of high cut rock slopes by an improved multi-output support vector machine method , 2016, Environmental Earth Sciences.

[4]  Genaro Daza Santacoloma,et al.  Parameter Selection in Least Squares-Support Vector Machines Regression Oriented, Using Generalized Cross-Validation , 2012 .

[5]  Xu Han,et al.  Time‐domain Galerkin method for dynamic load identification , 2016 .

[6]  R. Das,et al.  A simulated annealing-based inverse computational fluid dynamics model for unknown parameter estimation in fluid flow problem , 2012 .

[7]  Claude Daley.  Application of plastic framing requirements for polar ships , 2002 .

[8]  Kazuhiro Iijima,et al.  Loads for use in the design of ships and offshore structures , 2014 .

[9]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[10]  Pentti Kujala,et al.  Statistics of Ice Loads Measured on Mt Uikku in the Baltic , 2009 .

[11]  Samson B. Cooper,et al.  Static load estimation using artificial neural network: Application on a wing rib , 2018, Adv. Eng. Softw..

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  Kyungsik Choi,et al.  Estimation of local ice load by analyzing shear strain data from the IBRV ARAON's 2016 Arctic voyage , 2018 .

[14]  Jouko Karhunen,et al.  Inverse ice-induced moment determination on the propeller of an ice-going vessel , 2015 .

[15]  Junliang Gao,et al.  An engineering method for simulating dynamic interaction of moored ship with first-year ice ridge , 2019, Ocean Engineering.

[16]  Huang,et al.  Load identification of acoustic and vibration sources following linear regression and least-squares of generalized matrix inverse method , 2014 .

[18]  Eliz-Mari Lourens,et al.  Ice force identification on the Nordstrmsgrund lighthouse , 2016 .

[19]  Hongbo Zhao,et al.  Inverse analysis of geomechanical parameters by the artificial bee colony algorithm and multi-output support vector machine , 2016 .

[20]  Ron Ritch,et al.  Local ice pressures measured on a strain gauge panel during the CCGS Terry Fox bergy bit impact study , 2008 .

[21]  Roger Skjetne,et al.  Time-frequency analysis of acceleration data from ship-ice interaction events , 2018, Cold Regions Science and Technology.

[22]  Pentti Kujala,et al.  Analysis of short-term ice load measurements on board MS Kemira during the winters 1987 and 1988 , 2010 .

[23]  A. Tikhonov,et al.  Numerical Methods for the Solution of Ill-Posed Problems , 1995 .

[24]  Pentti Kujala,et al.  Semi-empirical evaluation of long term ice loads on a ship hull , 1996 .

[25]  Bernt J. Leira,et al.  Probabilistic methods for estimation of the extreme value statistics of ship ice loads , 2018 .

[26]  Jani Romanoff,et al.  Influence of load length on short-term ice load statistics in full-scale , 2017 .

[27]  Bernt J. Leira,et al.  Short term extreme statistics of local ice loads on ship hulls , 2012 .

[29]  J. H. Wilkinson,et al.  AN ESTIMATE FOR THE CONDITION NUMBER OF A MATRIX , 1979 .

[30]  Cheng Wang,et al.  A multi-strategy improved particle swarm optimization algorithm and its application to identifying uncorrelated multi-source load in the frequency domain , 2017, Neural Computing and Applications.

[31]  Pentti Kujala,et al.  Variation in short-term ice-induced load amplitudes on a ship's hull and related probability distributions , 2014 .

[32]  C. Ebinger,et al.  The geopolitics of Arctic melt , 2009 .

[33]  Ian Jordaan,et al.  Local ice pressures for multiyear ice accounting for exposure , 2010 .

[34]  Davide Chicco,et al.  Ten quick tips for machine learning in computational biology , 2017, BioData Mining.

[35]  Roger Skjetne,et al.  A method for real-time estimation of full-scale global ice loads on floating structures , 2018 .

[36]  Qian Zhang,et al.  Identification of Loads on Shield Tunneling Machines Based on PSO-SVM Method , 2013 .

[37]  Sami Saarinen,et al.  Ice crushing tests with variable structural flexibility , 2011 .

[38]  Garry Timco,et al.  A review of the engineering properties of sea ice , 2010 .

[39]  Sveinung Løset,et al.  Model tests of a submerged turret loading concept in level ice, broken ice and pressure ridges , 1998 .