ARTIFICIAL NEURAL NETWORK CORRECTION OF ROUGH ERRORS OF OBSERVATIONS*

In the context of tower measured radiation datasets.following the correction principle meeting a diagnostic equation in data quality control and in terms of a technique for model construction on data and ANN (artificial neural network) retrieval for BP correction of radiation measurements with rough errors available,a BP model is presented.Evidence suggests that the developed model works well and is superior to a convenient multivariate linear regression model,indicating its wide applications.     

高浓度黏性泥石流堆积层理结构中筛积层和粗化层形成机理的研究

根据高浓度黏性泥石流的观测资料,应用不同类型黏性泥石流的流变特性和流体结构的分类指标-流核比,对高浓度黏性泥石流堆积中的混杂层、筛积层和粗化层理结构进行了成因差异分析。侧重分析了砾石质点在高浓度黏性泥石流蠕动流场中作向上垂直运动的魏森伯效应,并在表面富集形成了筛积层的成因,及其它与粗化层结构的区别。     

运用人工鱼群算法的3D扫描碎片重建探究

针对传统三维碎片拼接匹配过程中依赖单一特征及存在误差累积的问题,提出了一种运用鱼群算法的全局最优匹配方法。该方法先对碎片点云数据进行多特征提取,结合纹理、专家经验信息对混合在一起的多种类型碎片进行粗糙集分类,之后采用鱼群算法的最优解求得最佳匹配方案。实例验证所提全局匹配方法具有能力强、与初始位置无关及较强的稳健性等特点,为三维碎片的全局匹配提供了一种有效的解决方案。     

利用TOPEX卫星高度计资料分析台湾岛周边海域巨浪和大风特征

卫星高度计实现了对全球性或区域性的海洋参量的实时监测,TOPEX卫星高度计提供了迄今为止时间序列最长、数据质量最高的全球海面风速和有效波高的同步观测资料。利用TOPEX卫星高度计资料,分析了有效波高4m以上的巨浪在台湾岛周边海域的时空分布特征,结果表明台湾岛周边海域巨浪的分布具有明显的季节特征。每年平均有效波高最大值大多数出现在夏季,春季是1a中有效波高最小的季节,而秋季和冬季是巨浪出现频率最高的季节。波高大于6m的巨浪大都出现在台湾岛东部及东北部海域,在南部海域出现较少。     

基于Monte Carlo-BP神经网络TBM掘进速度预测

预测隧道工程中TBM掘进速度,主要有完全经验的、半理论半经验的模型和人工智能等方法,所用参数均为确定性的,未考虑参数存在的随机性,故导致预测结果的不准确性。基于此,提出了Monte Carlo-BP神经网络TBM掘进速度预测模型,着重考虑了一些重要输入参数的随机性, 其中输入参数重要性的大小通过粗糙集进行计算排序。采用Monte Carlo产生随机数时,由于参量的样本数据的有限,分布函数均采用阶梯形经验分布函数。如果采用的数据是来自不同类型的 TBM,则应当考虑机器性能参数,并重新对参数重要性进行排序。实例计算表明,Monte Carlo-BP神经网络模型预测结果和实测值总体趋势和均值比较一致。     

Adaptive Predictive Inverse Control of Offshore Jacket Platform Based on Rough Neural Network

The offshore jacket platform is a complex and time-varying nonlinear system,which can be excited of harmful vibration by external loads.It is difficult to obtain an ideal control performance for passive control methods or traditional active control methods based on accurate mathematic model.In this paper,an adaptive inverse control method is proposed on the basis of novel rough neural networks (RNN) to control the harmful vibration of the offshore jacket platform,and the offshore jacket platform model is established by dynamic stiffness matrix (DSM) method.Benefited from the nonlinear processing ability of the neural networks and data interpretation ability of the rough set theory,RNN is utilized to identify the predictive inverse model of the offshore jacket platform system.Then the identified model is used as the adaptive predictive inverse controller to control the harmful vibration caused by wave and wind loads,and to deal with the delay problem caused by signal transmission in the control process.The numerical results show that the constructed novel RNN has advantages such as clear structure,fast training speed and strong error-tolerance ability,and the proposed method based on RNN can effectively control the harmfid vibration of the offshore jacket platform.     

弱地形上内潮生成问题——Ⅱ.粗糙地形情况下水深对内潮能通量的影响

前人在讨论水深对内潮能通量影响的时候得出结论:有限深海洋中海面对内潮的反射使得正压潮向内潮的能量转化相比较无限深海的情况显著降低,对于选定的地形,在无限深海假定下得到的能通量是该地形上内潮能通量的上限。鉴于前人所研究的基本上都是平滑的地形,而实际的海洋地形总是比较粗糙的,本文探讨了粗糙地形上内潮能通量随水深的变化。选取了弦函数地形、随机白噪声地形、弦函数地形叠加在高斯地形之上、随机白噪声地形叠加在高斯地形之上和随机白噪声地形与弦函数地形同时叠加在高斯地形之上5种情况进行了研究,发现对于这5种情况,都存在海洋有限深时的能通量大于无限深假定时的能通量,这说明前人得出的"有限深海洋中海面对内潮的反射使得正压潮向内潮的能量转化相比较无限深海的情况显著降低"的结论对于粗糙地形并不适用。     

Shear velocity estimates in rough‐bed open‐channel flow

Shear velocity u_* is an important parameter in geophysical flows, in particular with respect to sediment transport dynamics. In this study, we investigate the feasibility of applying five standard methods [the logarithmic mean velocity profile, the Reynolds stress profile, the turbulent kinetic energy (TKE) profile, the wall similarity and spectral methods] that were initially developed to estimate shear velocity in smooth bed flow to turbulent flow over a loose bed of coarse gravel (D₅₀ = 1·5 cm) under sub‐threshold conditions. The analysis is based on quasi‐instantaneous three‐dimensional (3D) full depth velocity profiles with high spatial and temporal resolution that were measured with an Acoustic Doppler Velocity Profiler (ADVP) in an open channel. The results of the analysis confirm the importance of detailed velocity profile measurements for the determination of shear velocity in rough‐bed flows. Results from all methods fall into a range of ± 20% variability and no systematic trend between methods was observed. Local and temporal variation in the loose bed roughness may contribute to the variability of the logarithmic profile method results. Estimates obtained from the TKE and Reynolds stress methods reasonably agree. Most results from the wall similarity method are within 10% of those obtained by the TKE and Reynolds stress methods. The spectral method was difficult to use since the spectral energy of the vertical velocity component strongly increased with distance from the bed in the inner layer. This made the choice of the reference level problematic. Mean shear stress for all experiments follows a quadratic relationship with the mean velocity in the flow. The wall similarity method appears to be a promising tool for estimating shear velocity under rough‐bed flow conditions and in field studies where other methods may be difficult to apply. This method allows for the determination of u_* from a single point measurement at one level in the intermediate range (0·3 < h < 0·6). Copyright © 2013 John Wiley & Sons, Ltd.     

ARTIFICIAL NEURAL NETWORK CORRECTION OF ROUGH ERRORS OF OBSERVATIONS

In the context of tower measured radiation datasets.following the correction principle meetinga diagnostic equation in data quality control and in terms of a technique for model construction ondata and ANN(artificial neural network)retrieval for BP correction of radiation measurementswith rough errors available,a BP model is presented.Evidence suggests that the developed modelworks well and is superior to a convenient multivariate linear regression model,indicating its wideapplications.