International Journal of Coastal, Offshore and Environmental Engineering
Volume:4 Issue: 1, Winter 2019

Nowadays, a huge amount of natural resources such as gases and oil are exploited from offshore oil fields and transported by pipes located at seabed. The pipelines are exposed to waves and currents and scour may occur around them. Subsequently, stability of the pipes can be threatened, so estimation and simulation of scouring around the pipes are quite vital. In this study, a hybrid method for simulating the scour depth in the vicinity of submerged pipes was developed. In other words, the adaptive neuro-fuzzy inference system (ANFIS) and the differential algorithm were combined with each other to simulate the scour depth. In general, ANFIS is an artificial neural network acts based on the Takagi-Sugeno inference system. This model is a set of if-then rules which is able to approximate non-linear functions. In addition, the differential algorithm is a powerful evolutionary algorithm among optimization algorithms which have many applications in scientific fields. In this study, the Monte-Carlo simulation was employed for examining the ability of numerical models. To validate the modeling results, the k-fold cross validation approach was also utilized with k=6. Then, the parameters affecting the scour depth were detected and six ANFIS and hybrid models were developed for scour estimation. After that, the results of the mentioned models were examined and this analysis showed that the superior model predicts scour values in terms of all input parameters. This model has reasonable accuracy. For example, the values of R and RMSE for this model were calculated 0.974 and 0.079, respectively. Furthermore, the analysis of the modeling results indicated that the ratio of the pipe distance from the sedimentary bed to the pipe diameter (e/D) was identified as the most effective parameter.

Construction of a new coastal structure changes the stable shape of the shoreline. This issue generally leads to sedimentation and erosion around adjacent structures due to changes in Littoral Sediment Transport (LST). This mechanism is considerably more complicated in crenulate-shaped bays than in straight shorelines. Therefore, special theories have been introduced for these bays. In addition to the above-mentioned difficulties, using two-dimensional long-term morphological models with considerable run times is not practical in most real cases. Instability and numerical errors may also be occurred due to the complicated forms of shorelines. The aim of this research is to introduce a proper morphological model for South-Eastern shorelines of Iran. Long term morphological simulation has been done for three important bays in the Mokran coasts using numerical and empirical models. The results show that these models are appropriate for understanding the behavior of crenulate-shaped bays. Their responses to natural changes like climate changes as well as human interventions can also be simulated properly.

The wave and current patterns of the Beris port and its surroundings before and after construction of the breakwater structure was investigated by numerical model, MIKE 21. For this purpose, the required data was provided and the model was prepared for implementation within a month from July 22 to August 21, 2016. In order to verify the modeling results, the extracted data were compared with the data derived from the global wave model; WAVEWATCH III and ECMWF. The simulation results show the significant effect of the breakwater on the stillness of the basin and the change in flow direction. According to the position of the port and the morphology of the coast, is expected to parallels sedimentation caused by waves and currents of the region focused on the long arm breakwaters and adjacent to the entrance mouth of breakwaters, as well as in the coastal part of the small arm of the breakwater.

Wave height forecasting is very important for coastal management and offshore operations. In this paper, the accuracy and performance of three soft computing techniques [i.e., Multi-Layer Perceptron (MLP), Radial Basis Function Neural Network (RBFNN) and Adaptive Neuro Fuzzy Inference System (ANFIS)] were assessed for predicting significant wave height. Using different combinations of parameters, the prediction was done over a few or a two days’ time steps from measured buoy variables in the Caspian Sea (case study: Anzali).  The data collection period was from 03.01.2017 to 06.01.2017 with 30-minute intervals. The performance of different models was evaluated with statistical indices such as root mean squared error (RMSE), the fraction of variance unexplained (FVU), and coefficient of determination (R2). Different simulations of performance assessment showed that the ANFIS techniques with requirements of past and current values of atmospheric pressures and height waves has more accuracy than the other techniques in the specified time and location. Meanwhile, in high lead times, the friction velocity decreases the accuracy of wave height forecasting.

One of the most important issues in the area of coastal structures design is determination of forces and loadings resulted from shallow water wave breaking. In the process of wave breaking, the subsequent particle motion is transformed from irrotational to rotational motion and due to this matter, vorticity and turbulence are generated and the sediment transport is affected by this phenomenon. Therefore, it is necessary to know about the location of wave breaking and other parameters such as the breaker height, breaker depth, etc. Over the last century, several formulas have been presented for predicting the wave breaking onset. These formulas depend on many parameters (e.g. seabed slope, water depth at the location of breaking, offshore wave height, etc.) that need to be known in order to obtain the desired wave breaking parameter (e.g. breaker height). In this study, some of the formulas for predicting wave breaking onset proposed in the recent decade are evaluated using the available laboratory data and it is tried to find out which formula is more suitable in different cases and conditions. A refinement process is carried out for choosing the appropriate data points out of all the available compiled laboratory data. The comparison is carried out in two phases. In the first one, the formulas are compared using all the data and in the second one, the comparisons are made based on the breaker type. These two phases yield to different outcomes. In the first phase, the formula proposed by Delavari et al. has the lowest values of bias, relative error, scatter index and root mean square error and the coefficient of determination of Goda’s formula is the highest. In the second phase, the data are categorized based on the plunging and spilling breaker types and the comparisons are made based on this categorization. The outcomes derived from the first phase are different from the ones derived from the second one.

Tuned sloshing dampers (TSDs) are applied to dissipate and absorb vibrational energy in structures. They can become an appropriate candidate for damping vibration in rotating offshore structures. In this study, the TSD systems are utilized in a semi-submersible platform in order to suppress its pitch motion response. First, the hydrodynamic behaviors of two different types of vessels are evaluated including a typical GVA4000 semi-submersible rig, and a floating oil storage tank using a finite element analysis. The results are compared with the available data from previous research, which the agreement is good. Subsequently, the semi-submersible platform equipped with four TSDs, which are located inside the bilge of pontoons and filled with 20% water is analyzed. It is analyzed in the frequency domain by considering the effect of internal fluid sloshing of TSDs. The results show that TSDs play a significant role for reducing the pitch motion response of the semi-submersible platform.