Application of BP Neural Network in Prediction of Cu-Pb Composite Plates Properties

Abstract： The artificial neural networks（ANN） , which have broad application, are proposed to develop Cu-Pb composite plates materials. Based on the back propagation（BP） algorithm of the forward muhilayer perceptron, the model to predict the shear stress under different ingredient of the third element and the hot dipping temperature for Cu-Pb composite plates are established. Then the relational model among the third element, hot dipping temperature and shear stress by using the limited data are studied, and the forecast average error is 4%. This model can satisfy the requirements of the precision of forecast in the project experiment process. The results show that the corresponding shear stress is greater when the third element in the element contains more Sn; the most appropriate temperature of hot-dip plating about is 340℃, ＇after predicted with lead/the third element/the best performance of copper composite material element of the third group is the one-element Sn, hot dip plating temperature is 335 ℃ ; two-element is 90% Sn 10% Bi, and hot dip plating temperature is 345 ℃. The prediction results can be used for a reference in instructing the further experimental design.     

Removing chlorine of CuCl residue from zinc hydrometallurgy by microwave roasting

Most Zn hydrometallurgy factories adopt Cu2SO4 as a dechlorination reagent from zinc solution nowadays, thus much CuCl residue is produced. The existing process of treating this residue is washing with water or sodium carbonate solution, which would cause a lot of troubles to water treatment and waste discharge. A method of microwave roasting was adopted for dechlorination of CuCl residue. A 1.5 kW microwave roasting equipment with dust collection and tail gas adsorption systems was set up and applied during the experiment. By investigating the effect of temperature, heat preservation time, moisture content of raw material and grain size of samples on the dechlorination, the optimal experimental condition is obtained. When the samples with 2% moisture and 〈150 μm grain size are microwave roasted at 400 °C for 2 h, the Cl content turns from 14.27% to 1.35% and the dechlorination rate is as high as 90%, while that with conventional heating is only 60%-80%. The phase change of the roasting process investigated with X-ray diffraction verifies that CuCl in CuCl residue is removed by being transformed into CuO.     

全风化花岗岩地层脉动灌浆控制防渗机理研究

针对全风化花岗岩地层的基础防渗加固,传统灌浆工艺限制于结构松散难以成孔起压,加剧了地基处理的难度。提出采用"钻灌一体,脉动灌浆"技术工艺;并利用数值模拟实现了不同脉动周期压力、钻灌时间控制参数下浆液渗透扩散规律及脉动周期压力下地层应力–应变的过程分析,通过脉动和稳压灌浆的浆液扩散与防渗影响范围对比,揭示了脉动灌浆防渗控制机理,得出了灌浆参数;结合黏土水泥浆灌浆材料进行了现场工程试验,现场试验验证了控制参数的合理性。试验表明,1.5~2.0 MPa脉动灌浆压力下,单排孔布设间距1 m,常规吕荣试验检查孔段次统计,透水率<2 Lu的占70%;疲劳吕荣试验透水率<3 Lu的比例为97%,透水率稳定区间为0.5~2.4 Lu;破坏吕荣试验透水率稳定区间为2~8.5Lu。灌浆后全风化、强风化地层的岩体完整性均有不同程度的提高,声波提升幅度范围为17.3%~52.5%。检查孔取出的芯样较完整,芯样抗压强度平均达7.3 MPa,且灌浆过程地层抬升小。研究成果对于全风化花岗岩以及同类地层具有较强的应用性,为此类地层防渗处理提供了一个可借鉴的工程案例。     

平行集束绝缘导线在农网改造中的应用

通过对农村低压电网改造现状的分析,针对平行集束绝缘导线的结构及特点,分析了其在电网改造中应用的优势,提出了平行集束绝缘导线应用过程中的注意事项,对其发展进行了展望.     

通信网业务参量的一个随机预测模型

利用离散时间型马尔科夫链及随机理论,构造了一个转移概率矩阵,并按照通信网业务特性,将需要预测的通信业务分为N个等级,定义了S={1,2,…,N}共N个状态空间,建立了通信网业务参量的随机预测模型。通过通信网的实例分析,说明了该模型的可靠性。