Simultaneous Titration of Ternary Mixtures of Pb(II), Cd(II) and Cu(II) with Potentiometric Electronic Tongue Detection

An automatic titration method is reported to resolve ternary mixtures of transition metals (Pb²⁺, Cd²⁺ and Cu²⁺) employing electronic tongue detection and a reduced number of pre‐defined additions of EDTA titrant. Sensors used were PVC membrane selective electrodes with generic response to heavy‐metals, plus an artificial neural network response model. Detection limits obtained were ca. 1 mg L^?1 for the three target ions and reproducibilities 3.0 % for Pb²⁺, 4.1 % for Cd²⁺ and 5.2 % for Cu²⁺. The system was applied to contaminated soil samples and high accuracy was obtained for the determination of Pb²⁺. In the determination Cd²⁺ and Cu²⁺, sample matrix showed a significant effect.     

参数灵敏度分析的神经网络方法及其工程应用

在系统分析中，参数灵敏度分析不仅为判断各系统参数的重要性大小提供了依据，量化的灵敏度指标也是后续参数估计的前提。然而，在多效实际系统中，系统参数与系统状态间的显式函数关系不易得到，导致一阶灵敏度指标无法直接求取。简化的单因素分析方法亦存在模型粗糙、精度不高的缺点。本文研究采用人工神经网络的高精度泛化映射，通过少量样本的训练，建立复杂系统中多个系统参数与系统状态间的近似映射关系，继而推导得到统一的灵敏度计算列式。简单结构的神经网络方法和解析方法的对比计算显示了方法的有效性和可靠性。最后，应用该法对某斜拉桥结构的荷载参数和刚度参数进行了考查，得到一般性结论。     

STABILITY ANALYSIS OF HOPFIELD NEURAL NETWORKS WITH TIME DELAY

ＩｎｔｒｏｄｕｃｔｉｏｎＩｎｒｅｃｅｎｔｙｅａｒｓｔｈｅｄｙｎａｍｉｃｂｅｈａｖｉｏｒｏｆｔｈｅｆｏｌｌｏｗｉｎｇＨｏｐｆｉｅｌｄｎｅｕｒａｌｎｅｔｗｏｒｋｓｍｏｄｅｌｗｉｔｈｔｉｍｅｄｅｌａｙｈａｖｅｂｅｅｎｉｎｖｅｓｔｉｇａｔｅｄｔｈｏｒｏｕｇｈｌｙＣｉ ｘｉ(ｔ) =-ｘｉＲｉ + ∑ｎｊ=1Ｔｉｊｆｊ(ｘｊ(ｔ-τｉｊ) ) +Ｉｉ　　 (ｉ=1 ,2 ,… ,ｎ) ,( 1 )ｗｈｅｒｅＲｉ,ＣｉａｎｄＩｉｒｅｐｒｅｓｅｎｔｒｅｓｉｓｔａｎｃｅ ,ｃａｐａｃｉｔａｎｃｅａｎｄｅｌｅｃｔｒｉｃｃｕｒｒｅｎｔ.Ｒｉ,Ｃｉａｒｅｐａ…     

Delay-independent exponential stability of stochastic Cohen–Grossberg neural networks with time-varying delays and reaction–diffusion terms

Different from the approaches used in the earlier papers, in this paper, the Halanay inequality technique, in combination with the Lyapunov method, is exploited to establish a delay-independent sufficient condition for the exponential stability of stochastic Cohen–Grossberg neural networks with time-varying delays and reaction–diffusion terms. Moreover, for the deterministic delayed Cohen–Grossberg neural networks, with or without reaction–diffusion terms, sufficient criteria for their global exponential stability are also obtained. The proposed results improve and extend those in the earlier literature and are easier to verify. An example is also given to illustrate the correctness of our results.     

基于动态神经元网络的激光陀螺输出误差模型

惯性敏感器误差补偿技术对提高武器装备的性能具有重要的意义,而误差补偿的关键在于误差模型的辨识。由于动态神经元网络是在前馈网络的节点引入前馈和反馈环节,理论上已证明其具有很强的动态逼近能力,可用来描述任意的非线性动态系统。根据惯性敏感器误差的动态特性,本探讨将动态神经元网络引入到激光陀螺误差建模中去,详细介绍了网络结构和对应的动态梯度算法。通过仿真算例说明,动态神经元网络在激光陀螺输出误差建模时具有一定的优点：网络收敛速度快、较好的跟踪性能、稳定性好。     

埋入压电元件的自诊断智能结构的理论分析与实验研究

将压电元件埋设于复合材料层板结构中，可实现结构应变分布的在线监测。本文提出一种采用压电应变传感器阵列和人工神经网络模型的自诊断方法，对局部埋入压电应变传感元件的平板结构进行了分析，采用神经网络模型根据压电传感器组的输出识别结构承载位置和大小，对该方法进行了数值模拟和实验验证。     

Numerical solution of Navier–Stokes equations using multiquadric radial basis function networks

A numerical method based on radial basis function networks (RBFNs) for solving steady incompressible viscous flow problems (including Boussinesq materials) is presented in this paper. The method uses a ‘universal approximator’ based on neural network methodology to represent the solutions. The method is easy to implement and does not require any kind of ‘finite element‐type’ discretization of the domain and its boundary. Instead, two sets of random points distributed throughout the domain and on the boundary are required. The first set defines the centres of the RBFNs and the second defines the collocation points. The two sets of points can be different; however, experience shows that if the two sets are the same better results are obtained. In this work the two sets are identical and hence commonly referred to as the set of centres. Planar Poiseuille, driven cavity and natural convection flows are simulated to verify the method. The numerical solutions obtained using only relatively low densities of centres are in good agreement with analytical and benchmark solutions available in the literature. With uniformly distributed centres, the method achieves Reynolds number Re = 100 000 for the Poiseuille flow (assuming that laminar flow can be maintained) using the density of , Re = 400 for the driven cavity flow with a density of and Rayleigh number Ra = 1 000 000 for the natural convection flow with a density of . Copyright © 2001 John Wiley & Sons, Ltd.     

Optimal design of non-equilibrium experiments for genetic network interrogation

Many experimental systems in biology, especially synthetic gene networks, are amenable to perturbations that are controlled by the experimenter. We developed an optimal design algorithm that calculates optimal observation times in conjunction with optimal experimental perturbations in order to maximize the amount of information gained from longitudinal data derived from such experiments. We applied the algorithm to a validated model of a synthetic Brome Mosaic Virus (BMV) gene network and found that optimizing experimental perturbations may substantially decrease uncertainty in estimating BMV model parameters.     

An intercausal cancellation model for Bayesian-network engineering

When constructing Bayesian networks with domain experts, network engineers often use the noisy-OR model, and causal interaction models more generally, to alleviate the burden of probability elicitation: the use of such a model serves to reduce the number of probabilities to be elicited on the one hand, and on the other hand forestalls experts having to give assessments for probabilities with compound conditions which they feel are hard to envision. Recently, we have shown that ill-considered use of the noisy-OR model specifically can substantially decrease a network's performance, especially in domains in which causal mechanisms include cancellation effects. Motivated by this observation, we designed a new causal interaction model, with the same engineering advantages as the noisy-OR model, to describe such effects. We detail properties of our intercausal cancellation model, and compare it against existing causal interaction models. We further illustrate the application of our model in the real-world domain of pharmacology.     

A Complete Solution to Spectrum Problem for Five‐Vertex Graphs with Application to Traffic Grooming in Optical Networks

A G‐design of order n is a decomposition of the complete graph on n vertices into edge‐disjoint subgraphs isomorphic to G. Grooming uniform all‐to‐all traffic in optical ring networks with grooming ratio C requires the determination of graph decompositions of the complete graph on n vertices into subgraphs each having at most C edges. The drop cost of such a grooming is the total number of vertices of nonzero degree in these subgraphs, and the grooming is optimal when the drop cost is minimum. The existence spectrum problem of G‐designs for five‐vertex graphs is a long standing problem posed by Bermond, Huang, Rosa and Sotteau in 1980, which is closely related to traffic groomings in optical networks. Although considerable progress has been made over the past 30 years, the existence problems for such G‐designs and their related traffic groomings in optical networks are far from complete. In this paper, we first give a complete solution to this spectrum problem for five‐vertex graphs by eliminating all the undetermined possible exceptions. Then, we determine almost completely the minimum drop cost of 8‐groomings for all orders n by reducing the 37 possible exceptions to 8. Finally, we show the minimum possible drop cost of 9‐groomings for all orders n is realizable with 14 exceptions and 12 possible exceptions.