AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Dynamic tension pdf4/30/2023 ![]() ![]() Through cases studied, it is proved that the trained LSTM-AM neural network model is suitable to estimate the mooring tension of underwater SYMS in complex sea states. Different variables are studied to determine the optimal structure of the LSTM-AM neural network model, such as the time window, the LSTM layer numbers, the LSTM layer unit numbers and the optimizer for neural network estimation performance. Meanwhile, the mooring tension is set as output target parameter. Those data are set as input features in the LSTM-AM neural network. The 6 degree-of-freedom motions of the FPSO are fetched from coupled analysis, together with the corresponding first-order and second-order central moments. The temporal development of the dynamic surface tension of heptanol-water. In this study, a neural network model named long-short term memory combined with attention mechanism (LSTM-AM) is adopted to estimate the mooring leg dynamic tension of underwater soft yoke mooring system in time domain. Droplets with diameters in the range between 100 and 200 m are produced by the controlled break-up of a liquid jet. It is significant to estimate the mooring tension for the safety, operation and maintenance of single point mooring system (SPM) of floating production, storage and offloading unit (FPSO). Flat dog-boned tensile specimens with dimensions of 10 mm × 3 mm × 0.8 mm for the quasi-static-tension tests and 10 mm × 4 mm × 0.8 mm for dynamic-tension experiments in terms of the gauge sections were electric-discharge machined with their longitudinal axes parallel to the rolling direction of sheets. ![]()
0 Comments
Read More
Leave a Reply. |