人工神经网络及其在窑炉动态温度场的模拟研究

本文阐述了人工神经网络的发展、基本原理以及前馈神经网络的反向传播学习算法，并应用单孢层网络进行了窑炉烧嘴温度场分布的仿真研究。结果表明。用非线性神经元网络模拟在窑炉温度场预测和控制方面是可行的。     

Development of bond strength model for FRP plates using back‐propagation algorithm

For the flexural reinforcement of bridge and building structure, synthetic materials whose dynamic properties are superior and those containing the merit of corrosion‐proof are widely used as the substitute for a steel plate. Since FRP plate has improved bond strength owing to the fibers externally adhering to the plate, many researches regarding the bond strength improvement have been substantially performed. To search out such bond strength improvement, previous researchers had ever examined the bond strength of FRP plate through their experiment by setting up many variables. However, since the experiment for a research on the bond strength takes much of expenditure for setting up the equipment and is time‐consuming, also is difficult to be carried out, it is limitedly conducted. The purpose of this study was to develop the most suitable artificial neural network model by application of various neural network models and algorithm to the data of the bond strength experiment conducted by previous researchers. Many variables were used as input layers against bond strength: depth, width, modulus of elasticity, tensile strength of FRP plate and the compressive strength, tensile strength, and width of concrete. The developed artificial neural network model has been applied back‐propagation, and its error was learned to be converged within the range of 0.001. Besides, the process for the over‐fitting problem has been dissolved by Bayesian technique. The verification on the developed model was executed by comparison with the test results of bond strength made by other previous researchers, which was never been utilized to the learning as yet. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 100: 5119–5127, 2006     

Effects of personal,psychosocial and occupational factors on low back pain severity in workers

Low back pain (LBP) remains the most common work-related musculoskeletal disorder (WMSD). While most of the LBP research has focused on occupational risk factors, other underlying causal mechanisms may exist since not all workers performing the same task develop an injury. Previous research has identified three primary risk factor categories for LBP (occupational, personal and psychosocial factors); however, few studies have investigated the impact of cross categorical risk factor interactions on LBP. The objective of this study was to investigate the effects of occupational, personal and psychosocial factors, and their interactions, on LBP severity in a population of workers currently suffering from LBP. Sixty LBP patients recruited for the study through local physicians and local announcements, completed questionnaires relating to identified occupational, personal and psychosocial risk factors, and completed an Oswestry Disability Index (ODI). Multiple regression models for predicting LBP severity were developed for each risk factor category and for a combined risk factor model (which included factors from all three risk factor categories) that included two-way interactions. Results showed that the final model consisted of both main effects and interaction terms between risk factor categories and had an adjusted R² value of 0.85, a significant improvement over models developed for the individual categories. These findings illustrate the need to consider all three broad categories of risk factors simultaneously in predicting injury status and in developing effective potential intervention efforts.     

基于AD7884的分离脱落电连接器机械分离力测试台的设计

基于分级型模数转换器AD7884对分离脱落电连接器的分离力进行测量,采用8位单片机W77E58与之接口,进行数据处理并通过485串口传输到上位机。实现了对分离脱落电连接器的分离力进行测量,系统运行稳定,且与上位机数据交互简单、可靠。     

碳四烃催化裂解制丙烯反应过程中尾气分析

采用2阀2柱HP6890气相色谱运行系统,通过HPPLOT/Al2O3"S"毛细管柱分析有机烃类,并用FID检测,13 X分子筛填充柱分析氢气,用TCD检测,建立了碳四烃催化裂解制丙烯反应尾气分析方法。结果表明:标准样品的分析结果标准偏差不大于4%,实际样品测试结果可保障物料平衡在98%以上。     

水中溶解性有机物分子量分布测定方法评价

文章介绍了两种测定水中有机物分子量分布的方法 :滤膜过滤法及凝胶液相色谱法 ,并列出了一些研究者用两种方法测定水源水的结果 ,根据两种方法的测定原理、测定步骤及对数据的分析 ,作者认为滤膜法应视作为一种粗略的方法 ,有条件时应尽量采用凝胶色谱法     

Adhesion-Delamination Mechanics of a Prestressed Circular Film Adhered onto a Rigid Substrate

A thin circular film clamped at the periphery is adhered to the planar surface of a rigid cylindrical punch. An external tensile load is applied to the punch, causing the film to delaminate from the substrate and the circular contact edge to contract. The film spontaneously separates from the punch, or pulls off, when the contact radius reduces to a range between 0.1758 and 0.3651 of the film radius, depending on the magnitude of the residual membrane stress. The mechanical delamination process is derived by a thermodynamic energy balance based on a coupled interfacial adhesion and residual membrane stress. The theoretical model has significant implications in nanoforce measurement, microelectromechanical systems (MEMS) comprising active moveable films, and biological cell adhesion.     

Accurate determination of hexanal in beef bouillons by headspace solid‐phase microextraction gas‐chromatography mass‐spectrometry

Lipid oxidation has great impact on the quality of food products through flavor and taste deterioration, reduction in nutritive value, and potential toxicity of the oxidized food components. Flavor and taste deterioration can be easily perceived and it represents one of the major causes of consumer complaints in the food industry. The deterioration of sensory properties is due to the decomposition products of hydroperoxides that easily isomerize and degrade into volatile compounds. Volatile products are responsible for flavor and taste deterioration. In this study, we present the development of the solid‐phase microextraction gas chromatography‐mass spectrometry (SPME‐GC‐MS) technique to quantify low amounts (μg/g range) of secondary oxidation products, i.e. hexanal. The optimization of SPME parameters is a difficult task because of the possibility of further formation of volatile products during analysis. Different parameters such as type of fiber, exposure time of the fiber to the sample headspace and the optimal temperature of absorption have also been investigated. The complete validation of the method was achieved by the determination of linearity, limits of detection and quantification and repeatability. We demonstrated that the SPME method is a valuable tool for the quantification of low amounts of secondary oxidation products such as hexanal. Therefore, this technique can be used to detect early formation of volatiles.     

三次谐波法控制的高速无刷电机转子结构研究

根据三次谐波反电势控制法对电机设计的要求,对平行充磁且极弧系数小于1、平行充磁且每极分2块、径向充磁且极弧系数为1共3种转子结构进行了研究.研究发现第一种和第二种结构均能在电机相绕组中产生足够大的三次谐波反电势.同时还对3种不同的转子结构引起的额定负载转矩下的转子涡流损耗进行了对比研究,结果表明,第三种结构引起的转子涡流损耗小于第一种结构,第一种结构引起的转子涡流损耗小于第二种.但是第三种结构应用较少,因为永磁体充磁时需要专门的工装夹具,加工困难.第一种结构和第二种结构容易实现.采用第一种结构制作了一台样机,并进行了实验验证,实验表明了设计的正确性.     

基于BP神经网络的集装箱箱号识别

提出一种用BP神经网络实现集装箱箱号识别的方法。提出的图像预处理方法对管柱,底面凹凸,脏污物、光线的强弱、倾斜、缺损或模糊有较强的适应性。在BP网络分类器实现时,考虑集装箱箱号的组成特点,采用并行处理方法。在BP算法中,引入动态因子,动态调整学习步长。实践证明利用这种方法来识别装箱箱号,速度快,识别率高,具有较高的实用价值。