Data mining in sloshing experiment database and application of neural network for extreme load prediction. (November 2021)

• Record Type: Journal Article
• Authors: Ahn, Yangjun; Kim, Yonghwan
• Is Part Of: Marine structures. Volume 80(2021)
• Publication Date: 2021-11
• Subjects: Sloshing -- Sloshing model test -- Data mining -- Artificial neural network -- Machine learning -- Sloshing load prediction; Naval architecture -- Periodicals; Offshore structures -- Periodicals; Architecture navale -- Périodiques; Structures offshore -- Périodiques; Naval architecture; Offshore structures; Periodicals; 620.4162
• DOI: 10.1016/j.marstruc.2021.103074
• Languages: English
• ISSNs: 0951-8339

Abstract

Abstract: Database of the sloshing model test has been mined. More than 540 terabytes experimental data have been accumulated for various cargo holds, vessels, environmental conditions, operational conditions, and experimental conditions. The database was organized, cleaned, and analyzed for the floating units larger than standard size LNG carriers or LNG fueled vessels. The selected target data was used for the machine learning to predict the model test results from the test conditions. An artificial neural network has been developed. Many different types of parameters were scaled and transformed as the input attributes followed by the optimization of the hyperparameters and the architecture. The network predicted the test results that were not used in the training process. The prediction results were validated according to the changes in the environmental conditions, operational conditions, and model dimensions. The accuracy of the network was acceptable to be applicable to the designing perspective. Highlights: The database of model-scale sloshing experiments is set up for ship cargo design. Data mining for sloshing impact pressure is introduced. Neural network scheme is applied for prediction of sloshing impact pressure. Actual cargoes of LNG carrier and LNG-fueled ship are considered for validating the developed scheme. The developed neural network scheme provides very good agreement with experimental data.