基于灵敏度分析的海洋油气资源BP神经网络预测模型的优化

作者针对BP神经网络结构设计中存在的问题,提出利用灵敏度分析方法对BP神经网络预测模型进行优化。通过BP算法与参数灵敏度分析的结合,寻找网络输入属性与输出属性之间的影响因子;在保证精度的前提下优选网络输入属性,简化网络结构,以增强网络的泛化能力,减少人为主观因素对网络设计的影响。最后以海洋油气资源预测为例,结合实测资料建立BP神经网络预测模型并进行了优化及预测精度评价,表明优化后的模型既能有效提高油气资源预测结果的稳定性,又不损失预测精度。     

An artificial neural network-based response surface method for reliability analyses of <Emphasis Type="Italic">c</Emphasis>-φ slopes with spatially variable soil

This paper presents an artificial neural network (ANN)-based response surface method that can be used to predict the failure probability of c-φ slopes with spatially variable soil. In this method, the Latin hypercube sampling technique is adopted to generate input datasets for establishing an ANN model; the random finite element method is then utilized to calculate the corresponding output datasets considering the spatial variability of soil properties; and finally, an ANN model is trained to construct the response surface of failure probability and obtain an approximate function that incorporates the relevant variables. The results of the illustrated example indicate that the proposed method provides credible and accurate estimations of failure probability. As a result, the obtained approximate function can be used as an alternative to the specific analysis process in c-φ slope reliability analyses.     

Experimental study of nonlinear behaviors of a free-floating body in waves

Nonlinear behaviors of a free-floating body in waves were experimentally investigated in the present study. The experiments were carried out for 6 different wave heights and 6 different wave periods to cover a relatively wide range of wave nonlinearities. A charge-coupled device (CCD) camera was used to capture the real-time motion of the floating body. The measurement data show that the sway, heave and roll motions of the floating body are all harmonic oscillations while the equilibrium position of the sway motion drifts in the wave direction. The drift speed is proportional to wave steepness when the size of the floating body is comparable to the wavelength, while it is proportional to the square of wave steepness when the floating body is relatively small. In addition, the drift motion leads to a slightly longer oscillation period of the floating body than the wave period of nonlinear wave and the discrepancy increases with the increment of wave steepness.     

The dependence of precipitation on wind direction over the Kuroshio front in the winter East China Sea

This study investigates atmospheric responses to the directions of surface wind over the Kuroshio front in the East China Sea, using wintertime satellite-derived data sets. Composite maps of sea surface temperature, wind speed, precipitation, turbulent heat flux, surface wind divergence, and the curl of wind vectors above the atmospheric boundary layer are depicted based on the classification of intense northeasterly (along the front) and northwesterly (across the front) winds over the East China Sea. When northeasterly winds prevail, considerable precipitation occurs on the offshore side of the Kuroshio front, in contrast to periods when northwesterly winds prevail. First, the northeasterly winds strengthen above the front because of the downward transfer of momentum from the fast-moving air at higher levels and/or an adjustment of sea level pressure over the oceanic front, although the process by which the influence of the Kuroshio penetrates beyond the marine atmospheric boundary layer remains unclear. Second, a cyclonic vortex forms above the marine atmospheric boundary layer (at 850-hPa height) on the offshore side of the front, and thereafter, surface wind convergence via Ekman suction (hence, enhanced precipitation) occurs over the East China Sea shelf breaks. The northeasterly winds blow over the East China Sea when the Aleutian Low retreats to the east and when high sea level pressure covers the northern Sea of Japan.     

黄东海夏、冬季颗石藻群落及其分布研究

2009年作者对中国黄东海海域夏季(7月20日至9月1日)与冬季(12月23日至2月5日)的两个季度月的颗石藻群落与分布进行调查研究。2009年夏季,中国黄东海海域调查区共发现21种颗石藻,其优势物种分别为赫氏艾密里藻(Emiliania huxleyi)、大洋桥石藻(Gephyrocapsa oceanica)、纤细伞球藻(Umbellosphaera tenuis)和深水花球藻(Florisphaera profunda)。颗石藻细胞丰度为0.23×103~17.62×103个/L,平均值为2.84×103个/L。2009年冬季,中国黄东海海域调查区共发现20种颗石藻,其优势物种分别为赫氏艾密里藻(E.huxleyi)、大洋桥石藻(G.oceanica)、深水花球藻(F.profunda)和纤细伞球藻(U.tenuis)。颗石藻的细胞丰度为0.12×103~35.35×103个/L,平均值为3.84×103个/L。本文系统地研究了颗石藻在我国黄、东海陆架海域的分布(特别是垂直分布),并对其作出了描述与分析,以期为关于中国海颗石藻群落分布等基础性研究提供可靠资料。     

Temporal variations in the current structure and volume transport of the Coastal Oyashio revealed by direct current measurement

Direct current measurements by a shipboard and bottom-mounted acoustic Doppler current profiler and concurrent hydrographic observations with a CTD were conducted off southeastern Hokkaido, Japan, between January and May 2005 to reveal temporal variations in the current structure and volume transport of the Coastal Oyashio (CO). The CO, which has a baroclinic jet structure with southwestward speeds exceeding 90 cm s^?1 and a width of 7–8 km, was associated with a surface-to-bottom density front and was formed on the offshore side of the shelf break. The volume transport of CO (T _CO) was estimated by integrating the fluxes of lower-density water that was trapped against the coast along the density front represented by the 26.2 σ _θ isopycnal line. This transport decreased monotonously from 0.79 Sv (1 Sv = 10⁶ m³ s^?1) in January to 0.21 Sv in March and subsequently to 0.12 Sv in May, possibly due to the decay of the East Sakhalin Current Water in the Okhotsk Sea. Accompanied by a decrease in T _CO, the location of the jet structure associated with the density front moved toward the coast while the maximum speed of the jet decreased and the tilt of the front became more horizontal. Consequently, more saline offshore Oyashio water flowed into the deep part of the shelf area, and the current structure altered from relatively barotropic in winter to baroclinic in spring. This study is the first to estimate the observed volume transport of the CO from direct current measurements.     

Radar-based collision avoidance for unmanned surface vehicles

Unmanned surface vehicles (USVs) have become a focus of research because of their extensive applications. To ensure safety and reliability and to perform complex tasks autonomously, USVs are required to possess accurate perception of the environment and effective collision avoidance capabilities. To achieve these, investigation into realtime marine radar target detection and autonomous collision avoidance technologies is required, aiming at solving the problems of noise jamming, uneven brightness, target loss, and blind areas in marine radar images. These technologies should also satisfy the requirements of real-time and reliability related to high navigation speeds of USVs. Therefore, this study developed an embedded collision avoidance system based on the marine radar, investigated a highly real-time target detection method which contains adaptive smoothing algorithm and robust segmentation algorithm, developed a stable and reliable dynamic local environment model to ensure the safety of USV navigation, and constructed a collision avoidance algorithm based on velocity obstacle (V-obstacle) which adjusts the USV’s heading and speed in real-time. Sea trials results in multi-obstacle avoidance firstly demonstrate the effectiveness and efficiency of the proposed avoidance system, and then verify its great adaptability and relative stability when a USV sailing in a real and complex marine environment. The obtained results will improve the intelligent level of USV and guarantee the safety of USV independent sailing.     

<Emphasis Type="Italic">H-M</Emphasis> bearing capacity of a modified suction caisson determined by using load-/displacement-controlled methods

This paper presents a series of monotonically combined lateral loading tests to investigate the bearing capacity of the MSCs (modified suction caissons) in the saturated marine fine sand. The lateral loads were applied under load- and displacement-controlled methods at the loading eccentricity ratios of 1.5, 2.0 and 2.5. Results show that, in the displacement-controlled test, the deflection-softening behavior of load-deflection curves for MSCs was observed, and the softening degree of the load-deflection response increased with the increasing external skirt length or the decreasing loading eccentricity. It was also found that the rotation center of the MSC at failure determined by the load-controlled method is slightly lower than that by the displacement-controlled method. The calculated MSC capacity based on the rotation center position in serviceability limit state is relatively conservative, compared with the calculated capacity based on the rotation center position in the ultimate limit state. In the limit state, the passive earth pressures opposite the loading direction under load- and displacement-controlled methods decrease by 46% and 74% corresponding to peak values, respectively; however, the passive earth pressures in the loading direction at failure only decrease by approximately 3% and 7%, compared with their peak values.     

Retardation of angular velocity of a rotating star due to mass loss

Variations of angular velocity of a rotating star on the upper main sequence due to mass loss driven by various mechanisms, like radiation, corpuscule ejection, and stellar wind, are examined. Expressions for the variations of angular velocity are derived by considering a model of a rotating star. The theoretical results show that the angular velocity decreaseswith time due tomass loss. The obtained results are applied to a hot fast-rotating star V1182 Aql (O9 V) and to Y Cyg (B0 V).