Anisotropic plasticity with application to sheet metals

Hill’s 1948 anisotropic theory of plasticity is extended to include the concept of isotropic–kinematic hardening. The “anomalous” effect can be accounted for by kinematic hardening. It is shown that the quadratic yield function can be used for sheet metals irrespective of its plastic strain ratio R. It is further shown that effects of thickness reduction due to further rolling may be accounted for by kinematic hardening.     

模糊神经网络在发动机故障诊断中的应用研究

对模糊逻辑和神经网络故障诊断方法做了研究,根据这两种方法各自的优缺点,采用串联方法将两者相结合,用模糊信息处理方法对输入信号进行预处理,然后利用神经网络的逼近能力来实现对故障的诊断.将该方法构建的推理系统应用于汽油发动机偶发性疑难故障诊断,仿真结果表明该方法可以给出较高精度的诊断结果.     

高压干燥器再生方式选择与应用

针对高压气体（≥10-42MPa）的特性和高压干燥器的结构特点，对其再生方式的选择与应用进行分析讨论。     

塑性分析在产品结构强度设计中的应用

通过分析有限元计算中结构模型简化与计算结果精度相互矛盾的现象,从考虑材料的塑性特性入手,介绍了如何在模型合理简化的条件下来提高计算结果的准确性。     

A model of one-surface cyclic plasticity and its application to springback prediction

This paper presents an elasto-plastic constitutive model based on one-surface plasticity, which can capture the Bauschinger effect, transient behavior, permanent softening, and yield anisotropy. The combined isotropic-kinematic hardening law was used to model the hardening behavior, and the non-quadratic anisotropic yield function, Yld2000-2d, was chosen to describe the anisotropy. This model is closely related to the anisotropic non-linear kinematic hardening model of Chun et al. [2002. Modeling the Bauschinger effect for sheet metals, part I: theory. International Journal of Plasticity 18, 571-95.]. Different with the model, the current model captures in particular permanent softening with a constant stress offset as well as the Bauschinger effect and transient behavior under strain path reversal. Inverse identification was carried out to fit the material parameters of hardening model by using uni-axial tension/compression data. Springback predicted by the resulting material model was compared with experiments and with material models that do not account for permanent softening. The results show that the resulting material model has a good capability to predict springback.     

人工神经网络在机械设计中的应用

本文通过对机械设计专家系统和人工神经网络的讨论，研究了人工神经网络和专家系统技术在机械设计智能系统中的综合应用问题，并提出了人工神经网络在机械设计中的总体应用方案，为进一步研究打下了基础。     

人工神经网络在降水预报中的应用

在用经验统计方法和降水判别函数进行24 h和12 h晴雨预报的基础上,再用B-P人工神经网络建立降水量级预报模型。经试用,预报准确率较高,有一定的应用价值,12 h预报准确率高于24 h预报准确率。     

The application neural networks in the process industry

This paper will present an overview of the history and definition of neural networks. Information will be presented on current neural network commercial products and their applications. A case history of neural network technology used in a chemical process application will be discussed along with recommendations of where neural networks may most effectively be used in the process industries.     

人工神经网络在智能机械设计中的应用

介绍了智能ＣＡＤ的概念和发展,分析了人工神经网络（ＡＮＮ）的特点,针对目前机械设计专家系统存在的问题,提出将ＡＮＮ应用到专家系统的设计中,是进行智能ＣＡＤ的一条有效途径。介绍了ＡＮＮ在概念设计、设计过程中形象思维的模拟、知识的获取和表示、回溯问题的模拟等方面的应用。     

神经网络技术在变压器故障诊断中的应用

本文针对变压器传统故障诊断的缺点,提出将神经网络技术用于变压器故障诊断。本文对BP算法改进,使网络收敛速度和误差精度进一步提高。收集部分油中溶解气体故障数据样本,对变压器故障类型进行了分析,并确定网络的输入和输出向量,建立诊断网络模型,实现对各项网络参数的比较确定,在Mtalab里面仿真使误差满足要求。     

模糊调整自适应神经网络在非线性系统中的应用

文中提出基于模糊调整的自适应神经网络控制策略,将其应用到非线性系统的仿真研究中.应用模糊推理机在线训练神经网络,同时构造了鲁棒控制器.仿真结果表明,该控制策略具有较快的调节速度和较好的稳定性.     

模糊神经网络在温控系统中的应用

文章首先介绍了温控系统的方案设计以及部分功能模块,然后介绍BP神经网络结构和模糊推理,在分析两者弊端的基础上提出将两者相结合的控制方法。本文还介绍了模糊神经网络的结构和学习方法,以及如何对训练样本进行预处理,最后利用matlab神经网络工具箱作为平台,通过测试样本仿真和试验,本设计的应用为实现快速、精确的温控系统提供了一种功耗低、经济有效的解决方案。     

遗传神经网络在工时定额计算中的应用

工时定额数据量大、影响因素多,使用常规拟合方法计算工时定额比较困难。为提高工时定额计算的正确性,采用人工神经网络技术,在MATLAB中建立了工时定额计算神经网络模型。针对BP神经网络存在易陷入局部最小值、收敛速度慢等不足,引入标准遗传算法来优化神经网络的权值和阈值。实验结果表明,基于实数编码的遗传算法优化速度快,优化后的神经网络迅速收敛,神经网络模型的测试误差低于5％。遗传神经网络可以克服单独使用神经网络时存在的缺点,训练好的模型在工时定额计算时正确性较高,有较好的实用价值。     

The application of mass spectrometry in molecular dosimetry: Ethylene oxide as an example

Mass spectrometry plays an increasingly important role in the search for and quantification of novel chemically specific biomarkers. The revolutionary advances in mass spectrometry instrumentation and technology empower scientists to specifically analyze DNA and protein adducts, considered as molecular dosimeters, derived from reactions of a carcinogen or its active metabolites with DNA or protein. Analysis of the adducted DNA bases and proteins can elucidate the chemically reactive species of carcinogens in humans and can serve as risk‐associated biomarkers for early prediction of cancer risk. In this article, we review and compare the specificity, sensitivity, resolution, and ease‐of‐use of mass spectrometry methods developed to analyze ethylene oxide (EO)‐induced DNA and protein adducts, particularly N7‐(2‐hydroxyethyl)guanine (N7‐HEG) and N‐(2‐hydroxyethyl)valine (HEV), in human samples and in animal tissues. GC/ECNCI‐MS analysis after HPLC cleanup is the most sensitive method for quantification of N7‐HEG, but limited by the tedious sample preparation procedures. Excellent sensitivity and specificity in analysis of N7‐HEG can be achieved by LC/MS/MS analysis if the mobile phase, the inlet (split or splitless), and the collision energy are properly optimized. GC/ECNCI‐HRMS and GC/ECNCI‐MS/MS analysis of HEV achieves the best performance as compared with GC/ECNCI‐MS and GC/EI‐MS. In conclusion, future improvements in high‐throughput capabilities, detection sensitivity, and resolution of mass spectrometry will attract more scientists to identify and/or quantify novel molecular dosimeters or profiles of these biomarkers in toxicological and/or epidemiological studies. © 2011 Wiley Periodicals, Inc., Mass Spec Rev 30:733–756, 2011     

Fine structure of olfactory epithelia of gastropod molluscs.

Among gastropod molluscs the chemical senses are most important for location of distant objects. They are used in food finding, locating mates, avoiding predators, trail following, and homing. Chemoreceptors are commonly associated with the oral area, the tentacles, and the osphradium, which lies in the mantle cavity. Most chemosensory neurons are primary sensory neurons, although secondary sensory cells have been reported in the osphradium of some prosobranch gastropods. Most chemosensory organs contain sensory cells with ciliated sensory endings that are in contact with the external environment. Some sensory endings have only microvilli or have no surface elaborations. Cilia on sensory endings are commonly of the conventional type, but some species have modified cilia; some lack rootlets, some have an abnormal microtubular content, and some have paddle-shaped endings. The perikarya of sensory neurons may be within the sensory epithelium, below it, or in ganglia near the sensory surface. In some groups of gastropods there are peripheral ganglia in the olfactory pathway; in others chemosensory axons appear to pass directly to the CNS. Olfactory epithelia of terrestrial pulmonates have modified brush borders with long branching plasmatic processes and a spongy layer of cytoplasmic tubules which extend from the epithelial cells. Sensory endings of the olfactory receptors are entirely within this spongy layer. Aquatic pulmonates may have a similar spongy layer in their olfactory epithelia, but the cilia of sensory endings, as well as motile cilia of epithelial cells, extend well beyond the spongy layer.     

Design of new sound metric and its application for quantification of an axle gear whine sound by utilizing artificial neural network

The gear whine sound of an axle system is one of the most important sound qualities in a sport utility vehicle (SUV). Previous work has shown that, because of masking effects, it is difficult to evaluate the gear whine sound objectively by using only the A-weighted sound pressure level. In this paper, a new objective evaluation method for this sound was developed by using new sound metrics, which are developed based on the increment of signal to noise ration and the psychoacoustic parameters in the paper, and the artificial neural network (ANN) used for the modeling of the correlation between objective and subjective evaluation. This model developed by using ANN was applied to the objective evaluation of the axle-gear whine sound for real SUVs and the output of the model was compared with subjective evaluation. The results indicate a good correlation of over 90 percent between the subjective and objective evaluations. This paper was recommended for publication in revised form by Associate Editor Yeon June Kang Professor Sang-Kwon Lee received a Ph.D. degree in ISVR (Institute of Sound and Vibration Research) from Southampton University in 1998. He joined Hyundai Motor Research Center in Korea, working with the Automotive Noise and Vibration Control Group from 1985 to 1994. He has been the Professor at the Department of Mechanical Engineering, Inha University, Inchon, Korea, since March 1999. His research interests are the digital signal processing, NVH (noise vibration harahness), condition monitoring, product sound quality design and active control.     

模糊神经网络技术在齿轮热分析中的应用

以单参数变化作为训练样本对模糊神经网络进行训练,定性地预测出多参数变化时齿轮发热量的变化趋势,有效完成了模糊神经网络技术在齿轮热分析中的应用。     

人工神经网络在机械故障诊断中的应用

针对传统的机械故障诊断方法的局限性,提出将人工神经网络应用于机械故障诊断中。由于BP算法存在收敛速度慢及易陷入局部极小等缺陷,利用实数编码改进遗传算法对神经网络的权值和阈值进行优化训练,并把训练好的神经网络用于机械振动信号预测及机械故障诊断中。通过对机械设备振动信号的预测,可以及早发现故障,及时消除故障隐患,为企业节省大量的维修时间和维修费用,提高企业的生产率。     

基于人工神经网络在注塑加工中的应用

注塑成形工艺参数优化一直是模具设计人员关注的问题。一般地,合理工艺参数的选择都是在现场凭经验加上反复试模获得的,这无疑带有许多盲目性且极大地依赖试模人员的经验。现有的注塑工艺OAE软件能够计算出给定工艺参数条件下的注塑成形情况,但无法求出给定注塑成形要求下的最佳工艺参数选择。借助人工神经网络（Artificial Neural Networks简称ANN）和优化技术,可以获得最佳工艺参数。