基于BP网络的反馈控制器设计

针对常规反馈控制器参数在对象时变情况下难以获得最优的问题，利用BP神经网络构成系统反馈控制器，通过自适应学习速率在线调整网络权值以逼近对象的逆动态模型，并利用Lyapunov方法给出了该算法的收敛的条件。将算法应用于循环水温度控制系统表明：该控制器对模型参数不依赖，能有效地适应控制对象参数的变化，系统具有较强的鲁棒性。     

THE TRANSFER BEHAVIOUR OF SOME CATIONS AT WATER／NITROBENZENE INTERFACE BY SEMIDIFFERENTIAL CYCLIC VOLTAMMETRY

The transfer of Sr~(2+) and Ba~(2+) ion, facilitated by 18-Crown-6 present in the aqueous phase, and of succinylcholine ion at w/nb interface were investigated by semi-differential cyclic voltammetry. A good polarographic curve of succinylcholine ion dissolved in water was obtained in the system of 0.01 mol/l LiCl (w)——0.01 mol/l TBATPB (nb). The peak current is directly proportional to the concentration of SC~(2+) ion. It can be used for the determination of SC and the detection limit is 1.05×10~(-5) mol/l.The apparent D~w and D~(nb) have been estimated. The transfer of Sr~(2+) and of Ba~(2+) at the interface are facilitated by 18-Crown-6 present in the aqueous phase and the peak current is directly proportional to the concentration of 18-Crown-6 in water. This method can be used for the determination of the complexing agent and for the stability constant of the complex formed in the aqueous phase.All the experimental results are in keeping with the theoretical.     

智能温度传感器在测控领域的应用

从智能传感器的发展现状出发,重点介绍了DS18B20、TMP101的性能和典型应用电路,并就其应用特点进行了比较,分析了智能温度传感器在测控领域的应用前景。     

W_(18)Cr_4V钢真空油淬白亮层、熔化层形成原因的试验研究

W_(18)Cr_4V钢真空加热油淬后,表面出现白亮层和熔化层等异常现象。本文利用金相显微镜,显微硬度计、扫描电子显微镜和电子探针等手段对白亮层和熔化层进行了分析研究。试验表明,白亮层、熔化层均是真空油淬增碳的结果。本文对白亮层、溶化层形成原因进行了比较深入的分析探讨提出了产生白亮层必须同时具备的三个条件。     

取代[14]轮烯,[18]轮烯和卟吩的异构体计数

用图论方法对取代〔１４〕轮烯、〔１８〕轮烯和卟吩的构造异构和构型异构体数进行计算。计算结果列表表示。     

Performance of Feedback BP Networks

ＰｅｒｆｏｒｍａｎｃｅｏｆＦｅｅｄｂａｃｋＢＰＮｅｔｗｏｒｋｓ￥ＬｕｏＳｉｗｅｉ；ＹａｎｇＷｕｊｉｅ＆ＺｈａｎｇＡｉｊｕｎ（Ｄｅｐｔ．ｏｆＣｏｍｐｕｔｅｒＳｃｉｅｎｃｅ＆Ｔｅｃｈｎｏｌｏｇｙ．ＮｏｒｔｈｅｒｎＪｉａｏｔｏｎｇＵｎｉｖｅｒｓｉｔｙ，Ｂｅ...     

神经网络在成组技术方面的应用

阐述了成组技术及其在高级制造技术中的作用，在此基础上描述了神经网络在零件编码分类系统中的应用以及用神经网络设计制造单元的方法。     

Quantitative genetic models of sexual selection

Summary Quantitative genetic models of sexual selection have disporven some of the central tenets of both the handicap mechanism and the sexy son hypothesis. These results suggest that the good genes approach to sexual selection may generally lead to erroneous results.Runaway sexual selection seems possible under a wide variety of circumstances. Quantittive genetic models have revealed runaway processes for sexually selected attributes expressed in both sexes and for attributes of parental care. Furthermore, the runaway could occur simultaneously in a series of populations that straddle an environmental gradient. While the models support the feasibility of runaway processes, empirical studies are needed to evaluate whether runaways actually happen. Estimates of critical genetic parameters are particularly needed, as well as measures of natural and sexual selection acting on the same population.The models also show that sexual selection has tremendous potential to produce population differentiation, particularly in epigamic traits. Differentiation is promoted by indeterminancy of evolutionary outcome, transient differences among populations during the final slow approach to equilibrium, sampling drift among equilibrium populations, and the tendency of sexual selection to amplify geographic variation arising from spatial differences in natural selection. Recent work with two- and three-locus models of sexual selection has produced results that parallel the results of the polygenic models^36–38,58. Thus the feature of indeterminate equilibria (outcome dependent on initial conditions) is common to both types of model.     

基于神经网络的眼底视杯图象分割技术

根据眼底图象中视杯的边沿特征,提出了一种基于ＢＰ神经网络的视杯分割方法,详述了这种方法的实现过程,并研究了ＢＰ学习算法的加速问题．实验证明,这种方法的分割效果较好．     

神经网络中误差反传算法的分析与改进

分析了ＢＰ网络存在的主要问题及其产生原因,提出了改进算法ＢＰＧ,以共轭梯度方向代替梯度方向进行搜索,并在学习过程中采用不精确的一维搜索、限幅和条件轮回等措施．计算机仿真结果表明：改进的ＢＰＧ算法优于原ＢＰ算法．