A NEW ALGORITHM FOR ADAPTIVE LATTICE FILTERAND ITS APPLICATION IN THE SPEECH LINEARPREDICTIVE SYNTHESIS

In this paper, an adaptive line spectral pair filter is derived from an adaptive lattice filter. A least-mean-square(LMS) type adaptive algorithm used to calculate directly the line spectral pair(LSP) coefficients on a stage-by-stage basis is presented. Experimental results show that the algorithm has higher convergence rate and lower misadjustment as compared with the other algorithms. The LSP coefficients calculated by the algorithm have been used to carry out speech linear predictive synthesis, resulting in better results than PARCOR coefficients.     

动态模糊神经网络在大坝变形预报中的应用

针对静态模糊神经网络的局限性,提出了在线动态建模的模糊神经网络方法.当新增样本进入训练集之后,根据新样本对模型的贡献大小,在已有模型的基础上进行动态修正,这样可以减少建模的计算时间.新方法实现了增加样本而矩阵阶数不增加,避免了矩阵求逆运算,理论上可以提高计算效率.实例表明动态模糊神经网络方法是可行的,可实现持久预报,具有较强的适应能力和较高的预报精度,可应用于在线实时变形预报及相关领域.     

Network traffic prediction based on a new time series model

Fast and accurate methods for predicting traffic properties and trend are essential for dynamic network resource management and congestion control. With the aim of performing online and feasible prediction of network traffic, this paper proposes a novel time series model, named adaptive autoregressive (AAR). This model is built upon an adaptive memory‐shortening technique and an adaptive‐order selection method originally developed by this study. Compared to the conventional one‐step ahead prediction using traditional Box–Jenkins time series models (e.g. AR, MA, ARMA, ARIMA and ARFIMA), performance results obtained from actual Internet traffic traces have demonstrated that the proposed AAR model is able to support online prediction of dynamic network traffic with reasonable accuracy and relatively low computation complexity. Copyright © 2005 John Wiley & Sons, Ltd.     

多属性神经网络地震反演在NB油田水平井钻探中的应用

NB油田位于渤海海域,为新近系河流相稠油油田,储层横向分布不稳定,砂体厚度薄、连通性较差,油水关系复杂,开发设计部署了大量水平井。选择神经网络反演方法,建立地震属性与储层参数的非线性关系,进而根据其关系反演得到储层参数数据体,利用该数据体沿层切片提取储层预测信息,研究储层发育规律,指导该油田水平井的部署和钻探,取得了较好的效果,降低了钻探风险。用神经网络地震反演方法进行储层预测研究,指导水平井钻探,在渤海海域尚属首次。     

疲劳裂纹的灰色残差预测

借助灰色理论，建立了预测疲劳裂纹扩展的灰色残差预测模型，并应用此模型预测了某不锈钢构件腐蚀疲劳裂纹的扩展，得到了较高精度的预测结果，为疲劳裂纹预测提供了一种简易而可靠的新途径。     

成形磨削中砂轮修整精度的研究

成形磨削一般采用金刚石笔来修整所需要的砂轮形状，金刚石笔在安装中的位置误差将影响被加工工件的精度，本文对此误差的大小进行了分析。     

双辊薄带钢连铸在线自动检测系统

介绍了双辊薄带钢连铸工艺,设计了双辊连铸机的计算机在线自动检测系统,通过采取正确的抗干扰措施提高了检测的精度,系统在双辊薄带钢连铸试验中应用效果良好.     

复射线展开法分析圆柱面对平面波散射的精度问题

讨论了用复射线展开法计算圆柱面对入射平面波散射时的计算误差特性，提出了控制其计算精度的复射线展开参数选择方法，证实了通过恰当选择展开参数可以有效地提升计算精度、实现误差控制。     

LASER ENHANCED ELECTROCHEMICAL MACHINING PROCESS

An experimental apparatus was designed and built for the hybrid process of laser enhanced electrochemical machining (ECM). Comparison experiments had been done between solely ECM and laser enhanced ECM. The machining performance of hybrid process was investigated and compared with solely ECM. The principle of the hybrid process was exposed by analyzing the microstructure of machining surface. The results show that the hybrid process has advantages in machining accuracy, surface quality, and machining efficiency.