Artificial neural network and finite element modeling of nanoindentation tests

This study first presents two-dimensional (2-D) axisymmetric and three-dimensional (3-D) finite element (FE) models of nanoindentation tests. Calculated load-displacement curves from the FE models are compared with the load-displacement curves from nanoindentation measurements on annealed copper. Numerical parametric studies are also performed to examine the effect of indenter geometry and the material’s stress-strain behavior on the load-displacement response. The 2-D and 3-D FE load-displacement curves compare well with the measured results on annealed copper. The second aspect of this study introduces a new modeling approach for indentation tests using artificial neural networks (ANN). In this approach, ANN models are generated to approximate the FE load-displacement curves for a wide range of material and geometric parameters. The ability of the ANN models to predict the indentation response is examined against other FE results not used as part of the training data. These models are shown to accurately predict the load-displacement behavior of a nonlinear homogeneous material as well as one with a hard film, such as an oxide film, on a relatively soft substrate. It is shown that the monotonic indentation load-displacement response during loading contains ample information for the ANN model to extract material flow properties of the indented material.     

基于RBF神经网络的WO3浸出率软测量建模

针对目前在钨碱煮浸出过程中,难以实现WO3浸出率的在线检测,依据钨矿碱煮浸出过程的化学反应机理以及影响浸出率的因素,提出软测量方案,采用人工神经网络建模方法,建立简便快速检测的软测量模型.根据工业现场采集的样本数据,运用Matlab工具训练好神经网络软测量模型,结果显示该软测量模型能够反应矿物浸出过程的实际状况,测量相对误差均值小于0.5%,能满足工业生产要求.该研究为实现钨浸出率的在线检测提供了一种新的方法.     

Artificial neural network based modeling of liquid membranes for separation of dysprosium

In recent years,the liquid membrane process has been widely investigated to remove rare earth metals.However,transport modeling of this process requires the accurate values of several parameters,which are difficult to measure.Thus,the accurate simulation of this process is a challenging task.In this study,the artificial neural network(ANN) based approach is used to model the liquid membrane process for removing dysprosium.Experimental results from a previous study were used to train the ANN.Init...     

Analysis and neural network modeling of the nonlinear correlates of habituation in the vestibulo-ocular reflex

Through the process of habituation, continued exposure to low-frequency (0.01 Hz) rotation in the dark produced suppression of the low-frequency response of the vestibulo-ocular reflex (VOR) in goldfish. The response did not decay gradually, as might be expected from an error-driven learning process, but displayed several nonlinear and nonstationary features. They included asymmetrical response suppression, magnitude-dependent suppression for lower- but not higher-magnitude head rotations, and abrupt-onset suppressions suggestive of a switching mechanism. Microinjection of lidocaine into the vestibulocerebellum of habituated goldfish resulted in a temporary dishabituation. This suggests that the vestibulocerebellum mediates habituation, presumably through Purkinje cell inhibition of vestibular nuclei neurons. The habituated VOR data were simulated with a feed-forward, nonlinear neural network model of the VOR in which only Purkinje cell inhibition of vestibular nuclei neurons was varied. The model suggests that Purkinje cell inhibition may switch in to introduce nonstationarities, and cause asymmetry and magnitude-dependency in the VOR to emerge from the essential nonlinearity of vestibular nuclei neurons.     

基于GA和BP网络的钢坯表面温度建模方法研究

主要研究步进式加热炉钢坯表面温度预报模型和在线补偿方法.针对机理建模的复杂性和辨识建模实验数据获得的困难性,提出基于GA和BP网络相结合的方法建立钢坯表面温度预报模型.使用GA初始化BP网络,避免了BP算法易陷入局部最优的缺点.在模型建立的基础上,利用BP算法进行在线补偿,从而使模型更加精确.仿真结果表明钢坯表面温度预报模型建立简单、精度高、适应性强.     

基于RBF神经网络的WO3浸出率软测量建模

针对目前在钨碱煮浸出过程中,难以实现 WO₃ 浸出率的在线检测,依据钨矿碱煮浸出过程的化学反应机理以及影响浸出率的因素,提出软测量方案,采用人工神经网络建模方法,建立简便快速检测的软测量模型.根据工业现场采集的样本数据,运用 Matlab 工具训练好神经网络软测量模型,结果显示该软测量模型能够反应矿物浸出过程的实际状况,测量相对误差均值小于 0.5 %,能满足工业生产要求.该研究为实现钨浸出率的在线检测提供了一种新的方法.      

计算机网络安全的分析与探索

针对计算机网络安全问题进行了探讨，分析了目前最为威胁网络安全的因素，介绍了网络安全的分类综合了一些保证网络安全的措施．     

Mechanisms of developmental regression in autism and the broader phenotype: A neural network modeling approach.

Loss of previously established behaviors in early childhood constitutes a markedly atypical developmental trajectory. It is found almost uniquely in autism and its cause is currently unknown (Baird et al., 2008). We present an artificial neural network model of developmental regression, exploring the hypothesis that regression is caused by overaggressive synaptic pruning and identifying the mechanisms involved. We used a novel population-modeling technique to investigate developmental deficits, in which both neurocomputational parameters and the learning environment were varied across a large number of simulated individuals. Regression was generated by the atypical setting of a single pruning-related parameter. We observed a probabilistic relationship between the atypical pruning parameter and the presence of regression, as well as variability in the onset, severity, behavioral specificity, and recovery from regression. Other neurocomputational parameters that varied across the population modulated the risk that an individual would show regression. We considered a further hypothesis that behavioral regression may index an underlying anomaly characterizing the broader autism phenotype. If this is the case, we show how the model also accounts for several additional findings: shared gene variants between autism and language impairment (Vernes et al., 2008); larger brain size in autism but only in early development (Redcay & Courchesne, 2005); and the possibility of quasi-autism, caused by extreme environmental deprivation (Rutter et al., 1999). We make a novel prediction that the earliest developmental symptoms in the emergence of autism should be sensory and motor rather than social and review empirical data offering preliminary support for this prediction. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Calvarial eosinophilic granuloma: diagnostic models and image feature selection with a neural network

We used thoracic SPECT to study the 99mTc-tetrofosmin (TF) uptake in patients with non-small-cell-lung-carcinoma (NSCLC). The results were compared with the percentage of P-glycoprotein (Pgp) found in flow cytometric analysis (FC) of samples of surgically-resected tumor tissue. MATERIAL AND METHODS: A total of 21 patients with NSCLC were studied by means 99mTC-TF and thoracic SPECT. Image analysis included the determination of the TF uptake rate in the lung mass with respect to that of healthy tissue of the contralateral lung. These rates were compared with the percentage of Pgp expression according to FC. FC analysis was also carried out in 16 samples of healthy lung tissue obtained from the patients. RESULTS: In healthy lung tissue, the mean Pgp expression according to FC was 4.58 +/- 1.87%. The cutoff value used to differentiate between Pgp positive and Pgp negative tumors was considered to be the mean plus two standard deviations (8.32). The Pgp-positive tumors (> 8.32%) presented significantly lower uptake levels (1.28 +/- 0.39) than the Pgp-negative lesions (1.66 +/- 0.33) (p = 0.029). CONCLUSIONS: There is a inverse correlation between the Pgp expression as determined by FC analysis and 99mTc-TF in NSCLC. Thus, this radiopharmaceutical provides rapid and non-invasive information on Pgp expression in these lesions.     

改进粒子群优化神经网络及其在产品质量建模中的应用

针对传统神经网络优化算法易陷入局部最优值的问题,在标准粒子群算法的基础上,对粒子速度与位置更新策略进行改进,提出一种基于改进粒子群优化算法的BP神经网络建模方法.使用sinc函数、波士顿住房数据及某钢厂带钢热镀锌生产的实际数据进行验证.结果表明,与标准的反向传播神经网络和支持向量机相比,基于改进粒子群优化的神经网络模型可以有效提高预测精度.     

神经网络控制系统的研究概况

本文介绍了神经网络控制系统的类型和研究概况，并对其存在的问题和发展趋势作了讨论。     

Computer image analysis in the study of endolymphatic hydrops

A team of authors investigated antibody levels against spermatozoa and against the zona pellucida in sera and peritoneal fluids in infertile women where diagnostic laparoscopy was indicated. The immunological cause of infertility was diagnosed in some women with a normal laparoscopic finding on the inner genital, as well as in patients with endometriosis and in women with adhesions. A minimal antibody response to antigens of gametes was recorded in women with the diagnosis of uterus myomatosus, uterus hypoplasticus and polycystic ovary. The authors present detailed findings on antibodies in different groups of patients.     

基于BP神经网络的VD过程温降预报模型

建立了基于BP神经网络的VD过程温降预报模型,利用五数总括值法和聚类分析法进行了BP神经网络输入数据的预处理,采用MINITAB软件确定了影响VD过程温降的主要因素为抽真空时间、保压时间、吹氩时间、非真空时间和钢水进VD过热度。利用245罐数据作为训练数据、50罐作为验证数据对模型进行了验证,结果表明:模型计算偏差在±5℃范围内的比例达到88%。     

A neural network model of the McCollough effect

Recent federal legislation has contained the stipulation that participating health maintenance organizations (HMOs) include a quality assurance program which stresses health outcomes. This provision was ostensibly directed at correcting alleged abuses in HMOs serving the urban poor. One version of the outcome method was employed for an 18-month period at an urban HMO caring for 2,000 Medicaid subscribers. The program involved comparing diagnostic accuracy and therapeutic outcomes for clinical conditions relevant to the study population with ideal standards established by the HMO. Three conditions were selected: contraception, depression, and hypertension. The results revealed widespread underdiagnosis (44-74%) in each condition and unacceptable therapeutic outcomes in two. Data collection was hampered by shifts in geography and financial eligibility among the denominator population and low response rates (38-63%) to telephone and mail surveys. Applying the general project guidelines to specific conditions proved considerably more difficult than anticipated. Further refinement of this approach to quality assessment must occur before its widespread use is feasible. Its effectiveness in improving quality remains to be seen. This experience raises doubts regarding the wisdom of legislating a specific outcome approach to quality assessment before feasibility and effectiveness have been demonstrated in organized health settings.     

Computer modeling of heat flow in welds

This paper summarizes progress in the development of methods, models, and software for analyzing or simulating the flow of heat in welds as realistically and accurately as possible. First the fundamental equations for heat transfer are presented and then a formulation for a nonlinear transient finite element analysis (FEA) to solve them is described. Next the magnetohydrodynamics of the arc and the fluid mechanics of the weld pool are approximated by a flux or power density distribution selected to predict the temperature field as accurately as possible. To assess the accuracy of a model, the computed and experimentally determined fusion zone boundaries are compared. For arc welds, accurate results are obtained with a power density distribution in which surfaces of constant power density are ellipsoids and on radial lines the power density obeys a Gaussian distribution. Three dimensional, in-plane and cross-sectional kinematic models for heat flow are defined. Guidelines for spatial and time discretization are discussed. The FEA computed and experimentally measured temperature field,T(x, y, z, t), for several welding situations is used to demonstrate the effect of temperature dependent thermal properties, radiation, convection, and the distribution of energy in the arc.     

Large neural network simulations on multiple hardware platforms

To efficiently simulate very large networks of interconnected neurons, particular consideration has to be given to the computer architecture being used. This article presents techniques for implementing simulators for large neural networks on a number of different computer architectures. The neuronal simulation task and the computer architectures of interest are first characterized, and the potential bottlenecks are highlighted. Then we describe the experience gained from adapting an existing simulator, SWIM, to two very different architectures-vector computers and multiprocessor workstations. This work lead to the implementation of a new simulation library, SPLIT, designed to allow efficient simulation of large networks on several architectures. Different computer architectures put different demands on the organization of both data structures and computations. Strict separation of such architecture considerations from the neuronal models and other simulation aspects makes it possible to construct both portable and extendible code.     

Computer modeling of the deformation of solid and hollow semifinished wheels on presses

Results obtained from mathematical modeling with the software package Deform 3D are used to demonstrate the feasibility of making railroad wheels from hollow semifinished products. Results are reported from modeling of the operations of upsetting on plane-parallel slabs, upsetting and fullering in a ring, and formation of the wheel. The conditions used in the modeling corresponded to the conditions encountered in actual wheel-making operations.     

基于神经网络方法的湿地生态脆弱性评价

应用BP神经网络模型对扎龙湿地的生态脆弱性进行了评价.采用7-2-4-1结构,以计算得到的各湿地类型样本栅格单元生态脆弱指数EⅥ值作为训练集,通过最大1 000次的误差反向传播训练,获得的最大误差是1.1%,最小误差0,成功实现了扎龙湿地7维评价指标变量到1维变量即扎龙湿地生态脆弱性指数的映射,得到了研究区全部栅格单元的生态脆弱性指数值.运用GIS技术,制得扎龙湿地生态脆弱性分级图,分析得出扎龙湿地中度脆弱和重度脆弱的地区占整体的18%,潜在脆弱地区和微度脆弱地区占整体的63%,从量化角度表明扎龙自然保护区整体生态环境不容乐观,为扎龙湿地生态环境保护和治理提供了具有科学意义的借鉴.