基于邻域统计特性的概率神经网络及其在自动目标识别中的应用

在概率神经的一种改进模型－ＦＤＯ网络的基础上，提出在设计网络收敛域时进一步考虑每一像素点周围８邻域的影响，对网络的作用函数加以修，使改进后的网络具有稳定性好且收敛速度快的优点。通过实验对改进前后网络的识别性能加以比较，证明改进后的网络特别适用于噪声图像的识别。     

人工智能方法用于熔喷过程在线检测的研究

熔喷生产最终产品质量的控制，对于过程优化具有重要的意义。产品质量的在线检测是过程监测与质量控制必不可少的。本文首次在熔喷系统中引入人工智能的研究方法，对熔喷非织造布的厚度与纤维直径进行在线预测。实测数据与人工神经网络的预测结果吻合较好，从而证实了人工神经网络用于模拟熔喷过程的可行性。网络的输入包括：挤出机温度、喷头温度、熔融体挤出速率、空气流率及接收距离。神经元计算的输出是纤维直径与熔喷非织布的厚度。文中进一步提出了将神经网络与专家系统相结合的研究路线，以实现熔喷过程的优化控制。     

用离子束混合及快速热处理方法形成钽的硅化物

本文描述用离子束透过钽金属膜进行混合和快速热处理方法来形成钽的硅化物.用溅射方法在P型硅衬底上淀积一层金属钽,然后用砷离子束透过钽金属模进行混合,采用快速热处理后形成了平整的硅化钽薄层.使用厚度为500埃的钽金属膜,得到钽的硅化物薄层电阻为5.5Ω/□.研究了砷离子能量、剂量及钽膜厚度对钽的硅化物薄层电阻的影响.用透射电镜和台阶仪对所形成的硅化钽进行了分析和厚度测量.     

Non‐reflecting artificial boundaries for transient scalar wave propagation in a two‐dimensional infinite homogeneous layer

This paper presents an exact non‐reflecting boundary condition for dealing with transient scalar wave propagation problems in a two‐dimensional infinite homogeneous layer. In order to model the complicated geometry and material properties in the near field, two vertical artificial boundaries are considered in the infinite layer so as to truncate the infinite domain into a finite domain. This treatment requires the appropriate boundary conditions, which are often referred to as the artificial boundary conditions, to be applied on the truncated boundaries. Since the infinite extension direction is different for these two truncated vertical boundaries, namely one extends toward x →∞ and another extends toward x→‐ ∞, the non‐reflecting boundary condition needs to be derived on these two boundaries. Applying the variable separation method to the wave equation results in a reduction in spatial variables by one. The reduced wave equation, which is a time‐dependent partial differential equation with only one spatial variable, can be further changed into a linear first‐order ordinary differential equation by using both the operator splitting method and the modal radiation function concept simultaneously. As a result, the non‐reflecting artificial boundary condition can be obtained by solving the ordinary differential equation whose stability is ensured. Some numerical examples have demonstrated that the non‐reflecting boundary condition is of high accuracy in dealing with scalar wave propagation problems in infinite and semi‐infinite media. Copyright © 2003 John Wiley & Sons, Ltd.     

Bioprocess applications of model-based estimation techniques

The last decade has seen the development of a number of approaches for estimating those variables which are difficult to measure on-line in industrial process situations. Whilst a range of techniques is available, a common element is the use of process knowledge in the form of a system model. In the case of bioprocess systems, although a large range of models has been presented in the literature, their use in estimation schemes on an industrial scale has been limited. A number of reasons can be identified for their low level of utilisation. Of particular significance is the uncertainty which exists in quantifying system performance and the process-model mismatch which inevitably results. The level of ‘pre-defined model’ uncertainty, together with the knowledge gained during the course of the fermentation, serves to dictate estimator structure. The paper considers a range of estimation strategies and contrasts, through industrial applications, their performance characteristics and utility.     

Dough mixing and breadmaking properties of quinoa-wheat flour blends

Flour blends of quinoa-wheat containing 0, 5, 10, 15, and 20% of manually dehulled quinoa meal or flour were evaluated for dough mixing and breadmaking properties and liking of the bread by a small panel. Increasing amounts of quinoa meal or flour increased farinograph absorption and dislike of bread for most of the panel. Dough development time increased with increase in meal but decreased with increase in quinoa flour. At 10% inclusion levels differences in liking from control 100% wheat flour bread were smaller for flour or water extracted meal to most of the panel, than with 10% non-extracted meal. This suggests that 10% inclusion of flour or water extracted meal may have potential for further investigation.     

SC文法功能体系

文法体系的研究一直是自然语言处理研究的核心问题之一.但是,由于自然语言本身所固有的复杂性和非规范性,多义问题始终未能得到圆满的解决.本文提出了SC文法(A SubCategory grammar for integrating Se-mantic and Case analysis),它是一种基于传统的上下文无关文法、语义文法,以及超前与反馈分析技术和格框架约束分析等技术的上下文相关处理文法.该文法不仅能继承传统的上下文无关文法的表示简洁、处理方便的特点,而且能实现语法和语义一体化分析和处理上下文相关以及复杂多义问题.     

四倍频Nd：YAG激光在高压氢气中的喇曼频移研究

利用Nd:YAG固体激光器四倍频输出(266nm)在高压H₂中的受激喇曼散射获得多波长的激光输出。当泵浦能量一定时,通过改变H₂压力得到了最佳的能量输出,299nm波长的激光能量为3mJ,341nm波长的激光能量输出为6.1mJ,398nm波长的激光能量输出为2.8mJ,239nm波长的激光能量输出为0.8mJ,同时在477nm,595nm,218nm,200nm波段也有能量输出。     

Dental amalgam – the effect of the technology of alloy powder preparation on the corrosion behaviour and the release of mercury

Dental amalgams are based on a broad spectrum of materials differing in their chemical composition, metallurgical treatment, and in the way the initial alloys powders are prepared. In addition to their chemical composition, amalgams based on various powders differ in both their microstructure and the amount of mercury needed for preparation. All these facts may affect electrochemical processes occurring during their interaction with oral fluids, and also mercury release. While verifying the effect of the technology used for the preparation of the high‐copper ternary alloy powder on the properties of resulting amalgams, this study aimed at the mechanism of their interaction with a model saliva solution as well as mercury release was included. Measurements were done in a model saliva solution using standard electrochemical methods and exposition measurements. The interaction of individual types of amalgams with artificial saliva did not reveal any significant differences. The free corrosion potential of all these amalgams in an aerated solution settled in the range of values in which tin oxidation, resulting in a layer of insoluble corrosion producsts, turned out to be the dominant anodic process. The rate of mercury release was the lowest for amalgams based on a gas‐atomized alloy. The highest rate of mercury release, and also its dependence on time, was exhibited by lathe‐cut powder based amalgam. In addition to different volume fraction of the Ag‐Hg phase and the level of its tin alloying, this different behaviour may be explained by differences in the rate at which a layer of tin corrosion products acting as a barrier to mercury release is formed.     

Application of artificial neural networks to the analysis of two‐dimensional fluorescence spectra in recombinant E coli fermentation processes

A two‐dimensional (2D) spectrofluorometer was used to monitor various fermentation processes with recombinant E coli for the production of 5‐aminolevulinic acid (ALA). The whole fluorescence spectral data obtained during a process were analyzed using artificial neural networks, ie self‐organizing map (SOM) and feedforward backpropagation neural network (BPNN). The SOM‐based classification of the whole spectral data has made it possible to qualitatively associate some process parameters with the normalized weights and variances, and to select some useful combinations of excitation and emission wavelengths. Based on the classified fluorescence spectra a supervised BPNN algorithm was used to predict some of the process parameters. It was also shown that the BPNN models could elucidate some sections of the process's performance, eg forecasting the process's performance. Copyright © 2005 Society of Chemical Industry