Artificial neural network for predicting values of residuary resistance per unit weight of displacement (original) (raw)
Related papers
Artificial neural networks for hull resistance prediction
2004
The applicability of artificial neural networks to the problem of ship resistance prediction as an alternative to more traditional statistical regression models has been investigated. In this work, an artificial neural network has been used as an interpolation tool to predict the residuary resistance of a systematic series of catamaran forms. It has been found that an artificial neural network is able to produce results of sufficient accuracy to be useful for preliminary prediction of vessel resistance, with the major benefits of: being relatively simple to set up; being easily retrained with new data; and that Froude number may be easily included as an independent variable.
Ocean Engineering, 2020
This article focuses on the use of an artificial neural network to estimate added resistance in regular head waves while using ship design parameters, such as length, breadth, draught or Froude number. In order to create a reliable model, only experimental data determined through model test measurements was used to train the neural network. This study showed that added wave resistance values predicted by the neural network soundly correlated with measured data and had good generalization ability. The developed neural network was presented in the form of mathematical function. This article presents examples of the use of this function to calculate added wave resistance. Functions presented here could have practical application in ship resistance analysis at the preliminary design stage. Added wave resistance can be determined through model test measurements or far-or near-field numerical methods. Far-field methods are most often based on momentum conservation theory (Maruo, 1960; Joosen, 1966 and Newman 1967) and the radiated energy approach (GERRITSMA and BEUKELMAN, 1972). Near-field numerical methods are based on pressure integration over a wetted hull surface and include approaches developed by Fujii and Takahashi (1975), SALVESEN (1978), FALTINSEN et al. (1980), Joncquez et al. (2008), Kuroda et al. (2008) and Kim and Kim (2011). Kashiwagi (2009) found satisfactory results using an enhanced unified theory using a modified approach by Maruo. Approximation methods based on semi empirical formulas were also used to estimate additional resistance. The common methods are STAWAVE-1 I STAWAVE-2 that have been developed by the Sea Trial Analysis-Joint Industry Project (Boom et al., 2013) and implemented by The International Towing Tank Conference in (ITTC, 2017). The STAWAVE-1 method estimates the added resistance of irregular waves caused by short head wave reflection, which depends on the waterline shape in the bow region. This method was developed for large ships with a high forward speed within trial conditions in mild waves. The STAWAVE-2 method was developed to approximate the transfer function of the added resistance in heading regular waves by using main ship characteristics. The sea keeping model test results from 200 ships were utilised to develop this method. The transfer function calculated by the use of STAWAVE-2 takes the mean resistance increase due to wave reflection and the motion induced resistance (ITTC, 2017) into account. Due to simple mathematical form and high accuracy, both STAWAVE methods are commonly used to estimate the added resistance and accuracy compare other methods. Liu and Papanikolaou (2016a, 2016b), developed various simple semi-empirical formulations for the rapid estimation of ship added resistance in head waves. They considered the effect of ship hull form characteristics, with best fitting from available experimental data for
Journal of Ship Production and Design, 2014
Mathematical representations for the resistance, trim, and wetted length of the Experimental Model Basin Series 50 have been developed using conventional regression analysis techniques as well as artificial neural networks. Series 50 is a standard series of 20 V-bottomed motor boats tested in 1941. These hulls could be representative of today's semidisplacement hulls. Recently, the series has been reanalyzed and published using contemporary planing coefficients, enabling resistance prediction in design stages. In the present study, mathematical representations are developed for the Series 50 as an alternative to using charts or data tables. Two methods are used, regression analysis and artificial neural networks. This study provides a useful resistance prediction method for designers and an opportunity to compare and contrast regression analysis and artificial neural networks applied to standard series. The main finding of the study is that both techniques were capable of developing stable and accurate models. A detailed quantification of the differences between methods is provided.
In this paper a neural network was designed and tested for estimating the cost of the activities and the hours of the activities in the shipping industry, by considering the ship parameters such as length of the ships, width, tonnage, etc. Multi-layered feed forward neural network trained by back-propagation algorithm was used in that work. Its results encouraged the research team to develop a new neural network model for representing also the indirect cost of ship construction. A neural network model was configured also for establishing the relationship between the cost of the activities and the indirect costs. The new network was trained by using data of eighteen different ships in order to finalize the design of four new ships.
Application of artificial neural networks to evaluation of ultimate strength of steel panels
Engineering Structures, 2006
Structural design of ships and offshore structures has been moving towards limit state design or reliability-based design. Improving the accuracy and efficiency of predicting ultimate strength of structural components, such as unstiffened panels and stiffened panels, has significant impact on our daily structural design. Empirical formulations have been widely used because of its simplicity and reasonable accuracy. In the past empirical formulations were generally developed by using regression analysis. The model uncertainties of good empirical formulations are around 10-15% in terms of coefficients of variation. In this paper artificial neural networks (ANN) methodology is applied to predict ultimate strength of unstiffened plates under uni-axial compression. The proposed ANN models are trained and cross-validated using the existing experimental data. Different ways to construct ANN models are also explored. It is found out that ANN models can produce more accurate prediction of ultimate strength of panels than the existing empirical formulae. The ANN model with five (original) input variables has slightly better accuracy than the model with three input variables. This demonstrates the capacity of ANN method to successfully establish a functional relationship between input and output parameters.
Resistance Prediction for Hard Chine Hulls in the Pre-Planing Regime
Polish Maritime Research, 2014
A mathematical representation of calm-water resistance for contemporary planing hull forms based on the USCG and TUNS Series is presented. Regression analysis and artificial neural network (ANN) techniques are used to establish, respectively, Simple and Complex mathematical models. For the Simple model, resistance is the dependent variable (actually R/Δ for standard displacement of Δ = 100000 lb), while the Froude number based on volume (FnV) and slenderness ration (L/V1/3) are the independent variables. In addition to these, Complex model’s independent variables are the length beam ratio (L/B), the position of longitudinal centre of gravity (LCG/L) and the deadrise angle (β). The speed range corresponding to FnV values between 0.6 and 3.5 is analyzed. The Simple model can be used in the concept design phases, while the Complex one might be used for various numerical towing tank performance predictions during all design phases, as appropriate
Journal of Marine Science and Engineering
The decrease in ship added resistance in waves fits into both the technical and operational measures proposed by the IMO to reduce the emissions of harmful gases from ships. Namely, the added resistance in waves causes an increase in fuel consumption and the emission of harmful gases in order for the ship to maintain the design speed, especially in more severe sea states. For this reason, it is very important to estimate the added resistance in waves with sufficient accuracy in the preliminary design phase. In this paper, the possibility of applying an ANN to evaluate added resistance in waves at the different sea states that the ship will encounter during navigation is investigated. A numerical model, based on the results of hydrodynamic calculations in head waves, and ANN is developed. The model can estimate the added resistance of container ships with sufficient accuracy, based on the ship characteristics, sailing speed, and the sea state using two wave energy spectra.
The article presents the use of multiple regression method to identify added wave resistance. Added wave resistance was expressed in the form of a four-state nominal function of: "thrust", "zero", "minor" and "major" resistance values. Three regression models were developed for this purpose: a regression model with linear variables, nonlinear variables and a large number of nonlinear variables. The nonlinear models were developed using the author's algorithm based on heuristic techniques. The three models were compared with a model based on an artificial neural network. This study shows that non-linear equations developed through a multiple linear regression method using the author's algorithm are relatively accurate, and in some respects, are more effective than artificial neural networks.
Response Prediction of Offshore Floating Structure using Artificial Neural Network
For deep-water oil and gas exploration, spar platform is considered to be the most economic and suitable offshore structure. Analysis of spar platform is complex due to various nonlinea rities such as geometric, variable submergence, varying pretention, etc. The Finite Element Method (FEM) is an important technique to cope with this kind of analysis. However, FEM is computationally very expensive and highly time-consuming process. Artificial Neural Network (ANNs) can provide meaningful solutions and can process information in extremely rapid mode ensuring high accuracy of prediction. This paper presents dynamic response prediction of spar mooring line using ANN. FEM-based time domain response of mooring line such as surge, heave and pitch is trained by ANN. Mooring line top tension is predicted after 2 hours response time histories of spar platform for various sea states. The response obtained using ANN is validated by conventional FEM analysis. Results show that ANN approach is found to be very efficient and it significantly reduces the time for predicting long response time histories.
SN applied sciences, 2020
This paper aims at establishing a framework for the development of artificial neural networks (ANNs) capable of realistically predicting the load-carrying capacity of reinforced concrete (RC) members. Multilayer back propagation neural networks are developed through the use of MATLAB and enriched databases which contain information describing the variation of load-carrying capacity in relation to key design parameters associated with the RC specimens (i.e. beams) considered. This work forms the basis for the development of a knowledge-based structural analysis tool capable of predicting RC structural response. A detailed discussion is provided on the different aspects of the proposed framework which include (1) the formation and analysis of the relevant (experimental) data, (2) the architecture of the ANNs, (3) the training/calibration process they undergo and finally, (4) ways of extending their applicability enabling them to predict the behaviour of RC structural forms with design parameters not represented in the available experimental database. Non-linear finite element analysis is used for validating the predictions of the ANN models developed. The comparative study reveals that the ANN models developed through the proposed framework are capable of effectively predicting the load-carrying capacity s of the RC structural forms considered quickly, accurately and without requiring significant computational resources. Keywords Artificial neural network • Database • Sampling method • Ultimate limit state • Reinforced concrete • Training process • Finite element analysis • Failure • Latin hypercube sampling List of symbols v Shear span b Width of the beam specimen cross-section d Effective depth of the beam specimen cross-section A s Area of longitudinal reinforcement acting in tension A sw Area of transverse reinforcement v ∕d Shear span to depth ratio f c Uniaxial compressive strength of concrete f yl Yield stress of longitudinal reinforcement bars f yw Yield stress of transverse reinforcement bars s Spacing between shear links l Ratio of tensile reinforcement (l = A s ∕b ⋅ d) w Ratio of transverse reinforcement (l = A sw ∕b ⋅ s) V u Shear strength Abbreviations CFP Compressive force path ANN Artificial neural network ULS Ultimate limit state LHS Latin hypercube sampling * Afaq Ahmad,