Neural adaptive robust control of underactuated marine surface vehicles with input saturation

This paper proposes a saturated tracking controller for underactuated autonomous marine surface vehicles with limited torque. First, a second-order open-loop error dynamic model is developed in the actuated degrees of freedom to simplify the design procedure. Then, a saturated tracking controller is designed by utilizing generalized saturation functions to reduce the risk of actuator saturation. This, in turn, improves the transient performance of the control system. A multi-layer neural network and adaptive robust control techniques are also employed to preserve the controller robustness against unmodeled dynamics and environmental disturbances induced by waves and ocean currents. A Lyapunov stability analysis shows that all signals of the closed-loop system are bounded and tracking errors are semi-globally uniformly ultimately bounded. Finally, simulation results are provided for a hovercraft vehicle to illustrate the effectiveness of the proposed controller as a qualified candidate for real implementations in offshore applications.     

Development of wavelet network model for accurate water levels prediction with meteorological effects

Accurate water levels modeling and prediction is essential for safety of coastal navigation and other maritime applications. Water levels modeling and prediction is traditionally developed using the least-squares-based harmonic analysis method that estimates the harmonic constituents from the measured water levels. If long water level measurements are not obtained from the tide gauge, accurate water levels prediction cannot be estimated. To overcome the above limitations, the current state-of-the-art artificial neural network has recently been developed for water levels prediction from short water level measurements. However, a highly nonlinear and efficient wavelet network model is proposed and developed in this paper for water levels modeling and prediction using short water level measurements. Water level measurements (about one month and a week) from six different tide gauges are employed to develop the proposed model and investigate the atmospheric changes effect. It is shown that the majority of error values, the differences between water level measurements and the modeled and predicted values, fall within the −5 cm and +5 cm range and root-mean-squared (RMS) errors fall within 1–6 cm range. A comparison between the developed highly nonlinear wavelet network model and the harmonic analysis method and the artificial neural networks shows that the RMS of the developed wavelet network model when compared with the RMS of the harmonic analysis method is reduced by about 70% and when compared with the RMS of the artificial neural networks is reduced by about 22%. It is also worth noting that if the atmospheric changes effect (meteorological effect) of the air pressure, the air temperature, the relative humidity, wind speed and wind direction are considered, the performance accuracy of the developed wavelet network model is improved by about 20% (based on the estimated RMS values).     

Estimation of scour around submarine pipelines with Artificial Neural Network

The process of scour around submarine pipelines laid on mobile beds is complicated due to physical processes arising from the triple interaction of waves/currents, beds and pipelines. This paper presents Artificial Neural Network (ANN) models for predicting the scour depth beneath submarine pipelines for different storm conditions. The storm conditions are considered for both regular and irregular wave attacks. The developed models use the Feed Forward Back Propagation (FFBP) Artificial Neural Network (ANN) technique. The training, validation and testing data are selected from appropriate experimental data collected in this study. Various estimation models were developed using both deep water wave parameters and local wave parameters. Alternative ANN models with different inputs and neuron numbers were evaluated by determining the best models using a trial and error approach. The estimation results show good agreement with measurements.     

Modelling of a medium-term dynamics in a shallow tidal sea, based on combined physical and neural network methods

The paper presents an approach towards a medium-term (decades) modelling of water levels and currents in a shallow tidal sea by means of combined hydrodynamic and neural network models. The two-dimensional version of the hydrodynamic model Delft3D, forced with realistic water level and wind fields, is used to produce a two-year-database of water levels and currents in the study area. The linear principal component analysis (PCA) of the results is performed to reveal dominating spatial patterns in the analyzed dataset and to significantly reduce the dimensionality of the data. It is shown that only a few principal components (PCs) are necessary to reconstruct the data with high accuracy (over 95% of the original variance). Feed-forward neural networks are set up and trained to effectively simulate the leading PCs based on water level and wind speed and direction time series in a single, arbitrarily chosen point in the study area. Assuming that the spatial modes resulting from the PCA are ‘universally’ applicable to the data from time periods not modelled with Delft3D, the trained neural networks can be used to very effectively and reliably simulate temporal and spatial variability of water levels and currents in the study area. The approach is shown to be able to accurately reproduce statistical distribution of water levels and currents in various locations inside the study area and thus can be viewed as a reliable complementary tool e.g., for computationally expensive hydrodynamic modelling. Finally, a detailed analysis of the leading PCs is performed to estimate the role of tidal forcing and wind (including its seasonal and annual variability) in shaping the water level and current climate in the study area.     

遗传小波神经网络在变形预报中的应用

目前常用的变形预报方法有BP人工神经网络和小波神经网络,但是都存在收敛速度慢且易受局部极值的影响。针对这两种算法的不足,本文利用遗传算法的全局寻优特性,将遗传算法与小波神经网络结合,形成遗传小波神经网,将其应用于变形预报,取得了良好的效果;并将算法的预报精度、稳定性、有效区间及运算时间作为评价算法优劣的4个标准,对BP神经网络、小波神经网络及遗传小波神经网络进行对比,结果表明遗传小波神经网络具有明显的优势。     

遥感、GIS结合与区域天然滑坡调查

以香港大屿山岛中部为试验研究区，探讨了遥感与GIS结合在区域滑坡调查中应用的可能性。在详细分析滑坡与环境因子关系后，将岩土类型、地貌、侵蚀、坡度等环境因子引入到影像中，与影像组成多源复合图像，可使地物的空间属性信息得到补充。同时采用适合高维复合数据的BP神经元网络对研究区天然滑坡进行识别，结果表明，区域滑坡的识别能力有较大提高。该方法的应用，将为大区域滑坡调查与监测奠定基础。     

第23太阳活动周的黑子数峰值特征预报

Using the characteristic values of sunspot number variations during the descent and ascent of solar cycles,a neural network is designed to make long-term predications of the ascending period and the maximum smoothed monthly mean sunspot number for the Solar Cycle　23. Moreover,the factor of geomagnetic disturbance is also added as an input. The trained and tested results from Solar Cycle 12 to 22 have been obtained. Finally,the predictions of the ascending period and the maximum smoothed monthly mean sunspot number are given for Solar Cycle 23.     

人工神经网络方法在地震预报中的初步应用

以陕西地区的地震为例，探讨了人工神经网络方法在地震预报中的应用。预报因子采用Ｋｅｉｌｉｓ－Ｂｏｒｏｋ提出的地震流函数。结果表明，人工神经网络方法能够较好地学习复杂的预报因子和预报对象的关系，模拟地震预报问题，预报效果也较好，有广阔的应用前景。     

Prediction of surface blast patterns in limestone quarries using artificial neural networks

This paper is an application of artificial neural networks (ANNs) in the prediction of the geometry of surface blast patterns in limestone quarries. The built model uses 11 input parameters which affect the design of the pattern. These parameters are: formation dip, blasthole diameter, blasthole inclination, bench height, initiation system, specific gravity of the rock, compressive and tensile strength, Young's modulus, specific energy of the explosive and the average resulting fragmentation size. Detailed data from a previous investigation were used to train and verify the network and predict burden and spacing of a blast. The built model was used to conduct parametric studies to show the effect of blasthole diameter and bench height on pattern geometry.     

关于BP神经网络转换GPS高程的若干问题

BP神经网络用于GPS高程转换有着较高的精度,但也存在不少问题,如网络的隐含层和隐含层单元个数选取、参加学习的样本的质量如何影响仿真精度等。结合实例分析上述问题,得出一些结论。