Parameters Inversion of Fluid-Saturated Porous Media Based on Neural Networks

The multi-layers feedforward neural network is used for inversion of material constants of fluid-saturated porous media. The direct analysis of fluid-saturated porous media is carried out with the boundary element method. The dynamic displacement responses obtained from direct analysis for prescribed material parameters constitute the sample sets training neural network. By virtue of the effective L-M training algorithm and the Tikhonov regularization method as well as the GCV method for an appropriate selection of regularization parameter, the inverse mapping from dynamic displacement responses to material constants is performed. Numerical examples demonstrate the validity of the neural network method.

Mechanics of a grip system of three-key-board hydraulic tongs developed for offshore oil pipe lines

This paper carries out the analysis of mechanics of a grip system of three-key-board hydraulic tongs developed for offshore oil pipe lines which has been successfully used in oil fields in China. The main improvement of this system is that a lever frame structure is used in the structural design, which reduces greatly the stresses of the major components of the oil pipe tongs. Theoretical analysis and numerical calculation based on thirteen basic equations developed Show that the teeth board of the tongs is not easy to slip as frequently happens to other systems and is of higher reliability.

Pattern Recognition With Weighted Complex Networks

In this paper we introduce a weighted complex networks model to investigate and recognize structures of patterns. The regular treating in pattern recognition models is to describe each pattern as a high-dimensional vector which however is insufficient to express the structural information. Thus, a number of methods are developed to extract the structural information, such as different feature extraction algorithms used in pre-processing steps, or the local receptive fields in convolutional networks. In our model, each pattern is attributed to a weighted complex network, whose topology represents the structure of that pattern. Based upon the training samples, we get several prototypal complex networks which could stand for the general structural characteristics of patterns in different categories. We use these prototypal networks to recognize the unknown patterns. It is an attempt to use complex networks in pattern recognition, and our result shows the potential for real-world pattern recognition. A spatial parameter is introduced to get the optimal recognition accuracy, and it remains constant insensitive to the amount of training samples. We have discussed the interesting properties of the prototypal networks. An approximate linear relation is found between the strength and color of vertexes, in which we could compare the structural difference between each category. We have visualized these prototypal networks to show that their topology indeed represents the common characteristics of patterns. We have also shown that the asymmetric strength distribution in these prototypal networks brings high robustness for recognition. Our study may cast a light on understanding the mechanism of the biologic neuronal systems in object recognition as well.

Case Study: Influence Of Morphological Changes On Flooding In Jingjiang River

The middle reach of the Yangtze River, customarily called the Jingjiang River, together with its diversion channels and Dongting Lake, form a large complicated drainage system. In the last five decades, significant geomorphological changes have occurred in the drainage system, including the shrinkage of diversion channels, contraction of Dongting Lake, changes in the rating curve at the Luoshan station, and cutoffs of the lower Jingjiang River. These changes are believed to be the cause of the occurrence of abnormal floods in the Jingjiang River. Qualitative analyses suggest that the first three factors aggravate the flood situation in the lower Jingjiang River, while the last factor seems beneficial for flood prevention. To quantitatively evaluate these conclusions, a finite-volume numerical model was constructed. A series of numerical simulations were carried out to test the individual and combined effects of the aforementioned four factors, and these simulations showed that high flood stages in the Jingjiang River clearly are related to the geomorphological changes.

On the formation of well-aligned ZnO nanowall networks by catalyst-free thermal evaporation method

Two-dimensional ZnO nanowall networks were grown on ZnO-coated silicon by thermal evaporation at low temperature without catalysts or additives. All of the results from scanning electronic spectroscope, X-ray diffraction and Raman scattering confirmed that the ZnO nanowalls were vertically aligned and c-axis oriented. The room-temperature photoluminescence spectra showed a dominated UV peak at 378 nm, and a much suppressed orange emission centered at similar to 590 nm. This demonstrates fairly good crystal quality and optical properties of the product. A possible three-step, zinc vapor-controlled process was proposed to explain the growth of well-aligned ZnO nanowall networks. The pre-coated ZnO template layer plays a key role during the synthesis process, which guides the growth direction of the synthesized products. (C) 2007 Elsevier B.V. All rights reserved.

Predicting chaotic time-series with wavelet networks

A new technique, wavelet network, is introduced to predict chaotic time series. By using this technique, firstly, we make accurate short-term predictions of the time series from chaotic attractors. Secondly, we make accurate predictions of the values and bifurcation structures of the time series from dynamical systems whose parameter values are changing with time. Finally we predict chaotic attractors by making long-term predictions based on remarkably few data points, where the correlation dimensions of predicted attractors are calculated and are found to be almost identical to those of actual attractors.

Optical interconnection for neural networks by use of a self-imaging function

A grating-lens combination unit is developed to form a scaling self-transform function that can self-image on scale. Then an array of many such grating-lens units is used for the optical interconnection of a two-dimensional neural network, and experiments are carried out. We find that our idea is feasible, the optical interconnection system is simple, and optical adjustment is easy. (C) 1998 Optical Society of America.