Forecasting tanker freight rate using neural networks

Improvement in forecasting accuracy is a difficult task but critical for business success. This paper investigates the potential of neural networks for short- to long-term prediction of monthly tanker freight rates. Procedures are outlined for the development of the neural networks. The problem of under-training and over-training is addressed by controlling the number of iterations during the training process of neural networks. A comparative study of predictive performance between neural networks and ARMA time series models is conducted. Our evience shows that neural networks can significantly outperform time series models, especially for longer-term forecasting.     

基于回声状态网络的船舶摇荡连续预报方法研究

回声状态网络（ ESNS）是一种新型递归神经网络,可通过对有限的已知样本进行训练,建立非线性模型来预报未知样本。该算法在解决非线性问题时具有一定优势。无需知道海浪的先验信息和船舶航行姿态的状态方程,仅利用实测的船舶横摇、纵摇历史数据,寻求规律即可进行实测摇荡数据的极短期预报。仿真结果表明,该算法在预报15 s以内可达到较高的预报精度,通过预报窗口的平移,可以进行连续在线预报。     

Application of the Grey topological method to predict the effects of ship pitching

Ship motion, with six degrees of freedom, is a complex stochastic process. Sea wind and waves are the primary influencing factors. Prediction of ship motion is significant for ship navigation. To eliminate errors, a path prediction model incorporating ship pitching was developed using the Gray topological method, after analyzing ship pitching motions. With the help of simple introduction to Gray system theory, we selected a group of threshold values. Based on an analysis of ship pitch angle sequences over 40 second intervals, a Grey metabolism GM（1,1） model was established according to the time-series which every threshold corresponded to. Forecasting future ship motion with the GM （1,1） model allowed drawing of the forecast curve with effective forecasting points. The precision of the test results show that the model is accurate, and the forecast results are reliable.     

Wave tranquility studies using neural networks

Information on heights of waves and their distribution around harbor entrances is traditionally obtained from the knowledge of incident wave, seabed and harbor characteristics by using experimental as well as numerical models. This paper presents an alternative to these techniques based on the computational tool of neural networks. Modular networks were developed in order to estimate wave heights in and around a dredged approach channel leading to harbor entrance. The data involved pertained to two harbor locations in India. The training of networks was done using a numerical model, which solved the mild slope equation. Test of the network with several alternative error criteria confirmed capability of the neural network approach to perform the wave tranquility studies. A variety of learning schemes and search routines were employed so as to select the best possible training to the network. Mutual comparison between these showed that the scaled conjugate method was the fastest among all whereas the one step secant scheme was the most memory efficient. The Brent's search and the golden section search routines forming part of the conjugate gradient Fletcher–Reeves update approach of training took the least amount of time to train the network per epoch. Calibration of the neural network with both mean square as well as the sum squared error as performance functions yielded satisfactory results.     

船舶柴油机NOx排放特性神经网络预测中的试验设计

研究船舶柴油机NOx排放特性神经网络预测中的学习样本选取试验设计方法。根据用于主机的船舶柴油机可能持续运行范围的工况变化特点,提出采用功率因素变边界的均匀设计法进行试验设计选取样本,并验证了其可行性。研究结果表明,变边界均匀设计法选取的样本用于神经网络训练,预测精度明显高于随机样本选取法。4位级变边界均匀设计法选取的样本训练得到的神经网络模型,NOx排放浓度预测误差小于3.8%,NOx比排放预测误差小4.5%。     

Time-series analysis of remote-sensed chlorophyll and environmental factors in the Santa Monica–San Pedro Basin off Southern California

The time-series of remote-sensed surface chlorophyll concentration measured by SeaWiFS radiometer from September 1997 to December 2001 and the relevant hydrological and meteorological factors (remote-sensed sea surface temperature, atmospheric precipitation, air temperature and wind stress) in Santa Monica Bay and adjacent waters off southern California were analyzed using wavelet and cross-correlation statistical methods. All parameters exhibited evident seasonal patterns of variation. Wavelet analysis revealed salient long-term variations most evident in air temperature during El Niño 1997–1998 and in wind stress during La Niña 1998–1999. Short-period (<100 days) variations of remote-sensed chlorophyll biomass were mostly typical to spring seasons. Chlorophyll biomass was significantly correlated with air temperature and wind stress: an increase of chlorophyll biomass followed with 5–6-day time lag an increase of wind stress accompanied by a simultaneous decrease of air temperature. The mechanism of these variations was an intensification of phytoplankton growth resulting from the mixing of water column by wind stress and entrainment of nutrients into the euphotic layer.     

智能式航迹自动舵的海上试验研究

简述了一类航还自动航的系统设计及仿真调试，重点介绍了实船试验情况，并通过海试比较了增益规划式PID、喜捧控制及神经网络控制等不同算法的性能。试验结果表明航迹自动舵在不同海况下长时间工作稳定可靠，航还控制性能良好。     

Comparing different contour methods with response-based methods for extreme ship response analysis

Environmental contours are often applied in probabilistic structural reliability analysis to identify extreme environmental conditions that may give rise to extreme loads and responses. They facilitate approximate long term analysis of critical structural responses in situations where computationally heavy and time-consuming response calculations makes full long-term analysis infeasible. The environmental contour method identifies extreme environmental conditions that are expected to give rise to extreme structural response of marine structures. The extreme responses can then be estimated by performing response calculations for environmental conditions along the contours.Response-based analysis is an alternative, where extreme value analysis is performed on the actual response rather than on the environmental conditions. For complex structures, this is often not practical due to computationally heavy response calculations. However, by establishing statistical emulators of the response, using machine learning techniques, one may obtain long time-series of the structural response and use this to estimate extreme responses.In this paper, various contour methods will be compared to response-based estimation of extreme vertical bending moment for a tanker. A response emulator based on Gaussian processes regression with adaptive sampling has been established based on response calculations from a hydrodynamic model. Long time-series of sea-state parameters such as significant wave height and wave period are used to construct N-year environmental contours and the extreme N-year response is estimated from numerical calculations for identified sea states. At the same time, the response emulator is applied on the time series to provide long time-series of structural response, in this case vertical bending moment of a tanker. Extreme value analysis is then performed directly on the responses to estimate the N-year extreme response. The results from either method will then be compared, and it is possible to evaluate the accuracy of the environmental contour method in estimating the response. Moreover, different contour methods will be compared.     

Bayesian statistical data assimilation for ecosystem models using Markov Chain Monte Carlo

This study considers advanced statistical approaches for sequential data assimilation. These are explored in the context of nowcasting and forecasting using nonlinear differential equation based marine ecosystem models assimilating sparse and noisy non-Gaussian multivariate observations. The statistical framework uses a state space model with the goal of estimating the time evolving probability distribution of the ecosystem state. Assimilation of observations relies on stochastic dynamic prediction and Bayesian principles. In this study, a new sequential data assimilation approach is introduced based on Markov Chain Monte Carlo (MCMC). The ecosystem state is represented by an ensemble, or sample, from which distributional properties, or summary statistical measures, can be derived. The Metropolis-Hastings based MCMC approach is compared and contrasted with two other sequential data assimilation approaches: sequential importance resampling, and the (approximate) ensemble Kalman filter (including computational comparisons). A simple illustrative application is provided based on a 0-D nonlinear plankton ecosystem model with multivariate non-Gaussian observations of the ecosystem state from a coastal ocean observatory. The MCMC approach is shown to be straightforward to implement and to effectively characterize the non-Gaussian ecosystem state in both nowcast and forecast experiments. Results are reported which illustrate how non-Gaussian information originates, and how it can be used to characterize ecosystem properties.     

采用非概率方法对不同环境条件下的漂浮式风力机进行系泊损伤识别（英文）

This paper discusses the damage identification in the mooring line system of a floating wind turbine(FWT) exposed to various environmental loads. The proposed method incorporates a non-probabilistic method into artificial neural networks(ANNs). The non-probabilistic method is used to overcome the problem of uncertainties. For this purpose, the interval analysis method is used to calculate the lower and upper bounds of ANNs input data. This data contains some of the natural frequencies utilized to train two different ANNs and predict the output data which is the interval bounds of mooring line stiffness. Additionally, in order to reduce computational time and more importantly, identify damage in various conditions, the proposed method is trained using constant loads(CL) case(deterministic loads, including constant wind speed and airy wave model) and is tested using random loads(RL) case(including Kaimal wind model and JONSWAP wave theory). The superiority of this method is assessed by applying the deterministic method for damage identification. The results demonstrate that the proposed non-probabilistic method identifies the location and severity of damage more accurately compared to a deterministic one. This superiority is getting more remarkable as the difference in uncertainty levels between training and testing data is increasing.     

Potential of a repair system for grouted connections in offshore structures: Development and experimental verification

Grouted connections are intensively used in offshore rigs, platforms as well as jacket and monopile offshore wind turbine structures. Being located in remote offshore conditions, these connections can experience considerable adverse loading during their lifetimes. Degradation was reported inside similar connections, which were installed in the last three decades. Grouting in the offshore sites may often be proven difficult, which eventually leads to reduced load-bearing capacity of connections in the long run. Thus, repair and rehabilitation of such connections should be planned ahead to minimize operational delays and costs. In this study, scaled grouted connections were manufactured using a novel mould, whose integrity were monitored using digital image correlation (DIC). The connections were loaded under static load to visualize the main failure pattern using distributed fibre optic sensors and acoustic emission (AE) analysis. Grouted connections were then repaired using a cementitious injectable grout. The effectiveness of the grout injection was monitored using dye penetration technique. Finally, specimens are reloaded to identify the potential of such repair for grouted connections.     

Hydrodynamic inline force prediction on vertical cylinders: a comparative study of neural network and its adaptive wavelets (wavenets)

The design of the neural network model and its adaptive wavelets (wavelet networks and wavenets) was used to estimate the wave-induced hydrodynamic inline force acting on a vertical cylinder. The data used to calibrate and validate the models were obtained from an experiment. In the brain, wavelet neural networks (WNNs) use wavelets to activate their hidden layers of neurons. In WNNs, both the position and dilation of the wavelets are optimized along with the weights. In one special approach to this kind of network construction, the position and dilation of the wavelets are fixed and only the weights of the network are optimized. In the present study, the neural network procedure and the above mentioned approach were employed to design a WNN, a so-called wavenet, using feed-forward neural network topology and its training method. Then, a comparison of these two methods was made. Numerical results demonstrate that both networks are capable of predicting hydrodynamic inline force. Furthermore, the combination of the neural network concept and the wavelet theory i.e. wavenet provides a more robust tool rather than standard feed-forward neural network, considering its more appropriate ability to predict any other data which the network had not experienced before. The results of this study can contribute to reducing the errors in future efforts to predict hydrodynamic inline force using WNNs, and thus improve the reliability of that prediction in comparison to the ANN and other methods. Therefore, this method can be applied to relevant engineering projects with satisfactory results.     

神经网络模型在港口吞吐量预测中的应用与误差分析

应用神经网络BP算法对杭州港的吞吐量预测实例进行了详细分析。通过对网络各种参数的调试与组合得出,当隐含层节点数为15,训练控制误差为0.035,分级迭代级数为4级,平滑因子参数为0.2,学习速率参数为1.5时,网络性能最佳。将网络预测结果与时间序列和回归分析2种方法进行了比较,得出神经网络方法在短期预测中要优于传统方法。通过对模型预测误差产生原因的简要分析,得出神经网络方法并不适用于吞吐量长期预测。最后对其应用过程中可能存在的一些问题提出了建议。     

基于多源信息聚融的港域航道智能监测系统

为通过对航道工程、数据挖掘、时空推理与航海新技术的深入研究,提出了基于时间序列的水文信息分析模型和基于神经网络的气象信息预测模型,实现了航道水文、气象信息预警功能,为管理者决策提供了数据支持。     

Filling up gaps in wave data with genetic programming

A given time series of significant wave heights invariably contains smaller or larger gaps or missing values due to a variety of reasons ranging from instrument failures to loss of recorders following human interference. In-filling of missing information is widely reported and well documented for variables like rainfall and river flow, but not for the wave height observations made by rider buoys. This paper attempts to tackle this problem through one of the latest soft computing tools, namely, genetic programming (GP). The missing information in hourly significant wave height observations at one of the data buoy stations maintained by the US National Data Buoy Center is filled up by developing GP models through spatial correlations. The gap lengths of different orders are artificially created and filled up by appropriate GP programs. The results are also compared with those derived using artificial neural networks (ANN). In general, it is found that the in-filling done by GP rivals that by ANN and many times becomes more satisfactory, especially when the gap lengths are smaller. Although the accuracy involved reduces as the amount of gap increases, the missing values for a long duration of a month or so can be filled up with a maximum average error up to 0.21 m in the high seas.     

基于聚类的港口吞吐量预测方法及其适用性分析

在统计分析历史数据的基础上,选取港口吞吐量、GDP值等指标,采用SPSS统计分析软件中的层次聚类分析法,将我国具有代表性的港口按照吞吐量增长规律分成平稳增长型、加速增长型和波动增长型3类。然后选择时间序列法、回归分析法、灰色模型理论和神经网络模型法,对不同类型的港口吞吐量预测的适用性进行了理论分析。最后以上海港和镇江港为实例进行计算,并对不同预测方法的适用性进行了验证。     

Changes in the design and operational wind due to climate change at the Indian offshore sites

The increasing global warming is most likely to affect the magnitude and pattern of wind at a regional level and such an effect may or not follow the trend predicted at the global scale. Regional level exercises are therefore necessary while making decisions related to engineering infrastructure. In this paper an attempt is made to know the extent of change in design as well as operational wind conditions at two offshore locations along the west coast of India. The design wind speeds with return periods of 10, 50 and 100 years derived for two 30-year time slices in the past and future are compared. In two separate exercises the past and future wind at the local level is simulated by empirical downscaling as well as by interpolation of the general circulation model (GCM) output. Both sets of past and future data are fitted to the Generalized Pareto as well as Weibull distributions using the peak over threshold method to extract long term wind speeds with a specified return. It is noticed that at the given locations the operational and design wind may undergo an increase of around 11%–14% when no downscaling is adopted and 14%–17% when the GCM data are downscaled. Although these figures may suffer from a certain level of statistical uncertainty the study points out to take a relook into the safety margins kept in the design and operation of ocean structures in the light of global warming.     

Forecasting the Suez Canal traffic: a neural network analysis

Although the Suez Canal is the most important man-made waterway in the world, rivaled perhaps only by the Panama Canal, little research has been done into forecasting its traffic flows. This paper uses both univariate ARIMA (Autoregressive Integrated Moving Average) and Neural network models to forecast the maritime traffic flows in the Suez Canal which are expressed in tons. One of the important strengths of the ARIMA modelling approach is the ability to go beyond the basic univariate model by considering interventions, calendar variations, outliers, or other real aspects of typically observed time series. On the other hand, neural nets have received a great deal of attention over the past few years. They are being used in the areas of prediction and classification, areas where regression models and other related statistical techniques have traditionally been used. The models obtained in this paper provide useful insight into the behaviour of maritime traffic flows since the reopening of the Canal in 1975—following an 8-year closure during the Arab–Israeli wars (1967–1973)—till 1998. The paper also compares the performance of ARIMA models with that of neural networks on an example of a large monthly dataset.     

Forecasting the Suez Canal traffic: a neural network analysis

Although the Suez Canal is the most important man-made waterway in the world, rivaled perhaps only by the Panama Canal, little research has been done into forecasting its traffic flows. This paper uses both univariate ARIMA (Autoregressive Integrated Moving Average) and Neural network models to forecast the maritime traffic flows in the Suez Canal which are expressed in tons. One of the important strengths of the ARIMA modelling approach is the ability to go beyond the basic univariate model by considering interventions, calendar variations, outliers, or other real aspects of typically observed time series. On the other hand, neural nets have received a great deal of attention over the past few years. They are being used in the areas of prediction and classification, areas where regression models and other related statistical techniques have traditionally been used. The models obtained in this paper provide useful insight into the behaviour of maritime traffic flows since the reopening of the Canal in 1975—following an 8-year closure during the Arab-Israeli wars (1967-1973)—till 1998. The paper also compares the performance of ARIMA models with that of neural networks on an example of a large monthly dataset.