Use this URL to cite or link to this record in EThOS:
Title: Neural network based simulation of sea-state sequences
Author: Bazargan-Harandi, Hamid
ISNI:       0000 0001 3452 2454
Awarding Body: Brunel University
Current Institution: Brunel University
Date of Award: 2006
Availability of Full Text:
Access from EThOS:
Access from Institution:
The present PhD study, in its first part, uses artificial neural networks (ANNs), an optimization technique called simulated annealing, and statistics to simulate the significant wave height (Hs) and mean zero-up-crossing period ( ) of 3-hourly sea-states of a location in the North East Pacific using a proposed distribution called hepta-parameter spline distribution for the conditional distribution of Hs or given some inputs. Two different seven- network sets of ANNs for the simulation and prediction of Hs and were trained using 20-year observed Hs’s and ’s. The preceding Hs’s and ’s were the most important inputs given to the networks, but the starting day of the simulated period was also necessary. However, the code replaced the day with the corresponding time and the season. The networks were trained by a simulated annealing algorithm and the outputs of the two sets of networks were used for calculating the parameters of the probability density function (pdf) of the proposed hepta-parameter distribution. After the calculation of the seven parameters of the pdf from the network outputs, the Hs and of the future sea-state is predicted by generating random numbers from the corresponding pdf. In another part of the thesis, vertical piles have been studied with the goal of identifying the range of sea-states suitable for the safe pile driving operation. Pile configuration including the non-linear foundation and the gap between the pile and the pile sleeve shims were modeled using the finite elements analysis facilities within ABAQUS. Dynamic analyses of the system for a sea-state characterized by Hs and and modeled as a combination of several wave components were performed. A table of safe and unsafe sea-states was generated by repeating the analysis for various sea-states. If the prediction for a particular sea-state is repeated N times of which n times prove to be safe, then it could be said that the predicted sea-state is safe with the probability of 100(n/N)%. The last part of the thesis deals with the Hs return values. The return value is a widely used measure of wave extremes having an important role in determining the design wave used in the design of maritime structures. In this part, Hs return value was calculated demonstrating another application of the above simulation of future 3-hourly Hs’s. The maxima method for calculating return values was applied in such a way that avoids the conventional need for unrealistic assumptions. The significant wave height return value has also been calculated using the convolution concept from a model presented by Anderson et al. (2001).
Supervisor: Bahai, H. ; Ozbayrak, M. ; Aryana, F. Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: Neural networks ; Simulation ; Neural networks ; Simulated annealing ; Finite elements method ; Pierson-Moskowitz spectrum ; Pile driving ; Hepta-parameter spline distribution ; Prediction ; Return value