Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures
Training of an artificial neural network (ANN) adjusts the internal weights of the network in order to minimize a predefined error measure. This error measure is given by an error function. Several different error functions are suggested in the literature. However, the far most common measure for re...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | Journal of Applied Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2014/759834 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568018136203264 |
|---|---|
| author | Niels H. Christiansen Per Erlend Torbergsen Voie Ole Winther Jan Høgsberg |
| author_facet | Niels H. Christiansen Per Erlend Torbergsen Voie Ole Winther Jan Høgsberg |
| author_sort | Niels H. Christiansen |
| collection | DOAJ |
| description | Training of an artificial neural network (ANN) adjusts the internal weights of the network in order to minimize a predefined error measure. This error measure is given by an error function. Several different error functions are suggested in the literature. However, the far most common measure for regression is the mean square error. This paper looks into the possibility of improving the performance of neural networks by selecting or defining error functions that are tailor-made for a specific objective. A neural network trained to simulate tension forces in an anchor chain on a floating offshore platform is designed and tested. The purpose of setting up the network is to reduce calculation time in a fatigue life analysis. Therefore, the networks trained on different error functions are compared with respect to accuracy of rain flow counts of stress cycles over a number of time series simulations. It is shown that adjusting the error function to perform significantly better on a specific problem is possible. On the other hand. it is also shown that weighted error functions actually can impair the performance of an ANN. |
| format | Article |
| id | doaj-art-a0ceb06f7e174dcb9f029dfd3537b8a5 |
| institution | Kabale University |
| issn | 1110-757X 1687-0042 |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Applied Mathematics |
| spelling | doaj-art-a0ceb06f7e174dcb9f029dfd3537b8a52025-02-03T00:59:52ZengWileyJournal of Applied Mathematics1110-757X1687-00422014-01-01201410.1155/2014/759834759834Comparison of Neural Network Error Measures for Simulation of Slender Marine StructuresNiels H. Christiansen0Per Erlend Torbergsen Voie1Ole Winther2Jan Høgsberg3DNV Denmark A/S, Tuborg Parkvej 8, 2900 Hellerup, DenmarkDet Norske Veritas, 7496 Trondheim, NorwayDepartment of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkDepartment of Mechanical Engineering, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkTraining of an artificial neural network (ANN) adjusts the internal weights of the network in order to minimize a predefined error measure. This error measure is given by an error function. Several different error functions are suggested in the literature. However, the far most common measure for regression is the mean square error. This paper looks into the possibility of improving the performance of neural networks by selecting or defining error functions that are tailor-made for a specific objective. A neural network trained to simulate tension forces in an anchor chain on a floating offshore platform is designed and tested. The purpose of setting up the network is to reduce calculation time in a fatigue life analysis. Therefore, the networks trained on different error functions are compared with respect to accuracy of rain flow counts of stress cycles over a number of time series simulations. It is shown that adjusting the error function to perform significantly better on a specific problem is possible. On the other hand. it is also shown that weighted error functions actually can impair the performance of an ANN.http://dx.doi.org/10.1155/2014/759834 |
| spellingShingle | Niels H. Christiansen Per Erlend Torbergsen Voie Ole Winther Jan Høgsberg Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures Journal of Applied Mathematics |
| title | Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures |
| title_full | Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures |
| title_fullStr | Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures |
| title_full_unstemmed | Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures |
| title_short | Comparison of Neural Network Error Measures for Simulation of Slender Marine Structures |
| title_sort | comparison of neural network error measures for simulation of slender marine structures |
| url | http://dx.doi.org/10.1155/2014/759834 |
| work_keys_str_mv | AT nielshchristiansen comparisonofneuralnetworkerrormeasuresforsimulationofslendermarinestructures AT pererlendtorbergsenvoie comparisonofneuralnetworkerrormeasuresforsimulationofslendermarinestructures AT olewinther comparisonofneuralnetworkerrormeasuresforsimulationofslendermarinestructures AT janhøgsberg comparisonofneuralnetworkerrormeasuresforsimulationofslendermarinestructures |