Condition Optimization of Reduction Roasting Magnetic Separation Technology for Laterite Nickel Ore by BP Neural Network Technique
-
摘要:
还原焙烧—磁选工艺可有效提取红土镍矿中的镍和铁等有价金属,由于影响红土镍矿还原焙烧—磁选效果的因素较多,导致工业生产中的选矿指标不稳定。为进一步提高还原焙烧—磁选工艺处理红土镍矿的效果,本研究以青海某镍矿为原料,采用正交试验与BP神经网络相结合的方法,对还原焙烧—磁选工艺的还原剂用量、焙烧温度、料层厚度、焙烧时间及磁场强度等因素进行了优化。结果表明:通过BP神经网络模型优化后的试验条件为还原剂用量9.5%、焙烧温度1 070℃、料层厚度10.0 mm、焙烧时间65 min及磁场强度2.5 kA·m-1,在此条件下可获得产率为30.29%的镍粗精矿,比采用正交试验最优因素组合条件所得的镍粗精矿产率提高了2.83%。
Abstract:Reduction roasting magnetic separation process can effectively extract nickel, iron and other valuable metals from laterite nickel ore. Due to the multiple factors existing in the process of reduction roasting magnetic separation of laterite nickel ore, the industrial indicators are unstable. In order to further improve the effect of reduction roasting magnetic separation process in laterite nickel ore, the factors of reducing agent dosage, roasting temperature, material thickness, roasting time and magnetic field intensity were optimized with a nickel ore in Qinghai as raw material by combining orthogonal experiment and BP neural network. The results showed that the optimized experimental conditions by BP neural network model are as follows: dosage of reducing agent 9.5%, roasting temperature 1 070 ℃, layer thickness 10.0 mm, roasting time 65 min and magnetic field strength 2.5 kA·m-1. Under these conditions, a rough nickel concentrate with a yield of 30.29% can be obtained, which is 2.83% higher than the yield of nickel rough concentrate obtained by using the optimal factor combination conditions of the orthogonal test.
-
表 1 试样中镍的物相分析结果
Table 1. Phase analysis results of nickel samples
相别 硅酸镍 硫酸镍 硫化镍 总镍 含量/% 0.450 0.031 0.100 0.581 分布率/% 77.45 5.34 17.21 100.00 表 2 正交试验各因素水平用量表
Table 2. Orthogonal diagram of experimental factors
因素 水平 1 2 3 4 A还原剂用量/% 5.0 10.0 15.0 20.0 B焙烧温度/℃ 800 900 1000 1100 C料层厚度/mm 10.0 20.0 30.0 40.0 D焙烧时间/min 30 45 60 75 E磁场强度/(kA·m-1) 1.0 1.5 2.0 2.5 表 3 正交试验安排及试验结果表
Table 3. Orthogonal diagram arrangement and results
试验编号 A B C D E 试验结果 水平 水平 水平 水平 水平 镍粗精矿产率/% 1 1 1 1 1 1 1.76 2 1 2 2 2 2 10.87 3 1 3 3 3 3 7.39 4 1 4 4 4 4 11.20 5 2 1 2 3 4 14.70 6 2 2 1 4 3 20.23 7 2 3 4 1 2 3.37 8 2 4 3 2 1 5.48 9 3 1 3 4 2 4.22 10 3 2 4 3 1 2.42 11 3 3 1 2 4 27.46 12 3 4 2 1 3 10.25 13 4 1 4 2 3 4.15 14 4 2 3 1 4 8.03 15 4 3 2 4 1 5.23 16 4 4 1 3 2 9.62 表 4 试验结果及网络仿真值
Table 4. Experimental result and its neural network simulation
试验编号 A B C D E 镍粗精矿产率/% 误差/% 水平 水平 水平 水平 水平 试验结果 神经网络仿真值 1 1 1 1 1 1 1.76 1.775 213 35 0.864 2 1 2 2 2 2 10.87 10.785 775 43 0.775 3 1 3 3 3 3 7.39 7.456 198 21 0.896 4 1 4 4 4 4 11.20 11.164 928 13 0.313 5 2 1 2 3 4 14.70 14.700 912 41 0.006 6 2 2 1 4 3 20.23 20.229 774 00 0.001 7 2 3 4 1 2 3.37 3.369 202 36 0.024 8 2 4 3 2 1 5.48 5.480 642 00 0.012 9 3 1 3 4 2 4.22 4.229 528 93 0.226 10 3 2 4 3 1 2.42 2.421 812 07 0.075 11 3 3 1 2 4 27.46 27.459 144 83 0.003 12 3 4 2 1 3 10.25 10.251 297 14 0.013 13 4 1 4 2 3 4.15 4.144 054 39 0.143 14 4 2 3 1 4 8.03 8.033 653 87 0.046 15 4 3 2 4 1 5.23 5.231 025 61 0.020 16 4 4 1 3 2 9.62 9.615 796 55 0.044 -
[1] 李小明, 白涛涛, 赵俊学, 等.红土镍矿冶炼工艺研究现状及进展[J].材料导报, 2014, 28(5):112-116. http://www.cqvip.com/QK/90370X/201405/49314566.html
[2] 杨涛, 李小明, 赵俊学, 等.红土镍矿处理工艺现状及研究进展[J].有色金属(冶炼部分), 2015(6):9-13. doi: 10.3969/j.issn.1007-7545.2015.06.003
[3] 李长玖, 陈玉明, 黄旭日, 等.镍矿的处理工艺现状及进展[J].矿产综合利用, 2012(6):8-11. http://www.cqvip.com/qk/97871x/201206/44203751.html
[4] 李光辉, 饶明军, 姜涛, 等.红土镍矿还原焙烧-磁选制取镍铁合金原料的新工艺[J].中国有色金属学报, 2011, 21(12):3137-3142. http://www.cnki.com.cn/Article/CJFDTotal-ZYXZ201112022.htm
[5] 曹志成, 孙体昌, 杨慧芬, 等.红土镍矿直接还原焙烧磁选回收铁镍[J].北京科技大学学报, 2010, 32(6):708-712. http://www.cnki.com.cn/Article/CJFDTotal-BJKD201006003.htm
[6] 郭爱克.神经计算科学[M].上海:上海科技出版社, 2001:69-81.
[7] 孙超, 庞昕.BP神经网络优化微生物浸矿工艺[J].生物加工过程, 2012, 10(6):65-69. doi: 10.3969/j.issn.1672-3678.2012.06.014
[8] 张翼, 王旭东.基于正交试验和BP人工神经网络的浮选药剂制度优化[J].有色金属(选矿部分), 2018(2):99-102. doi: 10.3969/j.issn.1671-9492.2018.02.021
[9] 李好泽, 郭汉杰.红土镍矿预还原焙烧的研究[J].铁合金, 2014, 45(4):40-45. doi: 10.3969/j.issn.1001-1943.2014.04.010
[10] 赵景富, 席增宏, 王刚.红土镍矿回转窑还原焙烧指标影响因素研究[J].铁合金, 2014, 45(3):17-19, 23. doi: 10.3969/j.issn.1001-1943.2014.03.006
[11] 王德志, 汪异, 程仕平, 等.料层厚度对还原钼粉性能的影响[J].中国钼业, 2007, 31(3):20-22. doi: 10.3969/j.issn.1006-2602.2007.03.006
[12] 贺峰.红土镍矿直接还原焙烧-磁选试验研究[D].西安: 西安建筑科技大学, 2013: 33-35.