Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures

The aim of this research is to examine key indicators that are necessary for the implementation and development of smart farming concepts in the agricultural industry, especially from the applied mobile technology point of view. Accordingly, the authors used a neural network based software solution to determine the correlation, relationship structure and partial contribution of indicators for the mobile technology development in agricultural industries in selected countries. The validity of the input-output model in a neural network based software solution was evaluated using the Minkowski error and Quasi-Newton method through several iterations/epochs. The neural network structure has shown the importance of particular indicators for adopting a mobile technology perspective in the agricultural industry, where the application of Information and Communications Technologies (ICT) in agriculture is most emphasized. Only those countries that invest the most in the ICT in the agricultural sector can achieve greater efficiency and productivity by applying smart farming.

show abstract

“…where E is error function, R is number 2, y k is output layer, x n is input layer, W is weights array, t is time (Christiansen et al, 2014).…”

Section: Economics Of Agriculturementioning

confidence: 99%

Smart farming in agricultural industry: Mobile technology perspective

Rađenović

Krstić

Marković

2020

Ekonomika poljoprivrede

View full text Add to dashboard Cite

show abstract

“…The aim of this study is to show that the ANN presented in Christiansen et al 5 can, in fact, be further optimized and reduced in size. The literature suggests a broad variety of pruning methods for optimizing the ANN architecture, and an overview over various pruning algorithms is given in the survey article of Reed.…”

Section: Introductionmentioning

confidence: 99%

“…A similar approach has recently been used by Christiansen et al 4 to reduce the simulation time dramatically when conducting a full fatigue life analysis of a mooring line on a floating platform. The same platform structure has been used in Christiansen et al 5 to investigate the influence of using different error measures or cost functions in the network training, and it was, furthermore, found that the resulting trained network used in that analysis simulated more than two orders of magnitude faster than a corresponding nonlinear numerical analysis.…”

Section: Introductionmentioning

confidence: 99%

Optimization of neural networks for time-domain simulation of mooring lines

Christiansen

Voie

Winther

et al. 2015

Proceedings of the Institution of Mechanical Engineers, Part M:

Self Cite

View full text Add to dashboard Cite

When using artificial neural networks in methods for dynamic analysis of slender structures, the computational effort associated with time-domain response simulation may be reduced drastically compared to classic solution strategies. This article demonstrates that the network structure of an artificial neural network, which has been trained to simulate forces in a mooring line of a floating offshore platform, can be optimized and reduced by different optimization procedures. The procedures both detect and prune the least salient network weights successively, and besides trimming the network, they also can be used to rank the importance of the various network inputs. The dynamic response of slender marine structures often depends on several external load components, and by applying the optimization procedures to a trained artificial neural network, it is possible to classify the external force components with respect to importance and subsequently determine which of them may be ignored in the analysis. The performance of the optimization procedures is illustrated by a numerical example, which shows that, in particular, the most simple procedures are able to remove more than half of the network weights in an artificial neural network without significant loss of simulation accuracy.

show abstract

“…One of the most promising alternatives to evaluate dynamic responses of marine structures with a significant reduction in computational time is the utilization of hybrid methods combining FEA with Artificial Neural Networks (ANNs) [1][2][3][4][5][6][7]. The basic idea of these methods is to employ the remarkable capacity of learning, generalization, and prediction of neural networks to replace the onerous numerical integration of a time domain dynamic analysis by finite elements method.…”

Section: Introductionmentioning

confidence: 99%

“…Pina et al [2] presented hybrid methods which use dynamic autoregressive models applied to the prediction of risers and mooring lines' top tensions. Christiansen et al [3,4] used a similar hybrid methodology in the prediction of top tensions for the fatigue assessment of a mooring line with a substantial reduction in the total simulation time. Chaves et al [5] studied the application of the hybrid method in the prediction of tension and curvatures in the bend stiffener region of a flexible riser and used these results to perform a fatigue verification.…”

Section: Introductionmentioning

confidence: 99%

Neural Networks Applied to the Wave-Induced Fatigue Analysis of Steel Risers

Cortina

Sousa

Sagrilo

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Time domain stochastic wave dynamic analyses of offshore structures are computationally expensive. Considering the wave-induced fatigue assessment for such structures, the combination of many environmental loading cases and the need of long time-series responses make the computational cost even more critical. In order to reduce the computational burden related to the wave-induced fatigue analysis of Steel Catenary Risers (SCRs), this work presents the application of a recently developed hybrid methodology that combines dynamic Finite Element Analysis (FEA) and Artificial Neural Networks (ANN). The methodology is named hybrid once it requires short time series of structure responses (obtained by FEA) and imposed motions (evaluated analytically) to train an ANN. Subsequently, the ANN is employed to predict the remaining response time series using the prescribed motions imposed at the top of the structure by the floater unit. In this particular work, the methodology is applied aiming to predict the tension and bending moments’ time series at structural elements located at the top region and at the touchdown zone (TDZ) of a metallic riser. With the predicted responses (tensions and moments), the stress time series are determined for eight points along the pipe cross sections, and stress cycles are identified using a Rainflow algorithm. Fatigue damage is then evaluated using SN curves and the Miner-Palmgren damage accumulation rule. The methodology is applied to a SCR connected to a semisubmersible platform in a water depth of 910 m. The obtained results are compared to those from a full FEA in order to evaluate the accuracy and computer efficiency of the hybrid methodology.

show abstract

Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures

Cited by 29 publications

References 11 publications

Smart farming in agricultural industry: Mobile technology perspective

Smart farming in agricultural industry: Mobile technology perspective

Optimization of neural networks for time-domain simulation of mooring lines

Neural Networks Applied to the Wave-Induced Fatigue Analysis of Steel Risers

Contact Info

Product

Resources

About