摘要
本文介绍了以铋冶炼浸渣为原料。利用碳酸氢铵转化法合成三盐基硫酸铅的工艺原理;在碳酸氢铵转化过程中,通过设计正交实验,系统探讨影响铅转化率的主要因素,并且通过BP神经网络为实验结果建模,模拟结果与实验结果比较吻合,说明了模型准确可靠,同时将所建立的神经网络嵌入到遗传算法中,通过遗传算法寻求系统的最优结果,得到的最优操作条件分别为:NH_4HCO_3/Pb摩尔比2.56,反应时间2.3 h,HAc/浸渣比0.6%(wt%),液固比1.2,铅转化率可以达到98.26%。
The processing principle of synthesizing tribasic lead sulphate from bismuth hydrometallurgy waste residue through ammonium hydrogen carbonate transformation was introduced. The affecting factors on in the processing of ammonium hydrogen carbonate transformation were studied through an orthogonal test and the result was modeled by BP neural network. The simulated value was fitted closely to experimental value, illuminating the accuracy and reliability of the model. Meanwhile the neural network was embedded into the genetic algorithms to search for the optimum result. The optimum condition obtained was: NH4 HCO3/Pb = 2.56 (mole ratio), reaction time t = 2.3 h, HAc/waste residue delt with acid = 0.6% ( wt% ), liquid/solid = 1.2. The reclaiming rate of Pb obtained was up to 98.26%.
出处
《计算机与应用化学》
CAS
CSCD
北大核心
2006年第10期967-970,共4页
Computers and Applied Chemistry
基金
江西省科技厅社发重点研究资助项目(2004027)
南昌大学青年基金(2005035)
南昌大学测试基金(2005010)
关键词
铋冶炼浸渣
碳酸氢铵转化
BP神经网络
遗传算法
bismuth hydrometallurgy waste residue, ammonium hydrogen carbonate, BP neural network, genetic algorithms