基于径向基神经网络和遗传算法的槽内式选择性超声电合成甲基苯甲醛

doi:10.7503/cjcu20131043

摘要/Abstract

摘要：

以混合二甲苯为原料, Mn(Ⅲ)为氧化剂, 硫酸溶液为电解质, 采用槽内式超声电合成甲基苯甲醛. 探讨了选择性电合成甲基苯甲醛的可能性, 通过径向基(RBF)神经网络和遗传算法(GA)对选择性电合成甲基苯甲醛3种异构体的比例、电流效率与混合二甲苯的用量、硫酸浓度和电流强度的关系建立预测模型, 并运用GA确定模型中RBF神经网络的目标均方误差(Goal)和径向基函数的分布(Spread). 然后根据预测模型, 使用GA对电合成条件进行优化, 分别获得了电合成产物中对位甲基苯甲醛占优、邻位和对位甲基苯甲醛占优以及电流效率最高时的电合成条件. 当采用上述条件进行实验时, 模型给出的预测结果分别为: 对位甲基苯甲醛占优的质量分数可达90.01%, 邻位和对位甲基苯甲醛占优的质量分数为80.38%, 电流效率达到最高时的邻位、间位和对位甲基苯甲醛的质量分数分别为16.80%, 8.43%和74.77%; 而与之相对应的实际实验结果分别为90.10%和79.91%, 以及17.20%, 8.49%和74.31%, 二者之间的最大相对误差小于±2.24%, 表明所建立模型的预测值与实测值基本吻合.

关键词: 甲基苯甲醛, 超声电合成, 选择性电合成, 人工神经网络, 遗传算法

Abstract:

Methyl benzaldehyde was synthesized via in-cell ultrasonic electrosynthesis with xylene mixture as raw material, Mn(Ⅲ) as oxidant and sulfuric acid as the electrolyte. The feasibility of the selective electrosynthesis of methyl benzaldehyde was discussed. The relation between experimental results(i.e. three methyl benzaldehyde isomer ratio of selective synthesis, current efficiency) and experimental conditions(i.e. xylene mixture concentration, sulfuric acid concentration and the current strength) were explored using radial basis function(RBF) neural network and genetic algorithm(GA)in the electrosynthesis process, and moreover, the prediction model was established. The mean squared error goal(Goal) and the spread of radial basis functions values(Spread) of the RBF neural network in prediction model were optimized by GA. Then electrochemical synthesis conditions, whenever 4-methyl benzaldehyde dominated, 2-methyl benzaldehyde and 4-methyl benzaldehyde dominated, or the current efficiency reached highest, were optimized by GA according to prediction model. In accordance with these conditions, the prediction results of model were given as follow: first, the percent content of 4-methyl benzaldehyde dominated was 90.01%; second, the percent content of 2-methyl benzaldehyde and 4-methyl benzaldehyde dominated was 80.38%; third, the percentage of 2-methyl benzaldehyde, 3-methyl benzaldehyde and 4-methyl benzaldehyde were 16.80%, 8.43% and 74.77%, respectively when the current efficiency reached the highest. The corresponding actual experiment results were 90.10%, 79.91% and 17.20%, 8.49%, 74.31%, respectively. The maximum relative error between prediction results and experiment results was less than ±2.24%. It showed that the model’s prediction results were in agreement with experimental results.

Key words: Methyl benzaldehyde, Ultrasonic electrosynthesis, Selective electrosynthesis, Arpngicialneural network, Genetic algorithm

中图分类号:

O621.3

TrendMD:

张汇, 何玉韩, 唐铎, 李彦威. 基于径向基神经网络和遗传算法的槽内式选择性超声电合成甲基苯甲醛. 高等学校化学学报, 2014, 35(6): 1199.

ZHANG Hui, HE Yuhan, TANG Duo, LI Yanwei. In-cell Selective Ultrasonic Electrosynthesis of Methyl Benzaldehyde Based on RBF Neural Network and Genetic Algorithm^†. Chem. J. Chinese Universities, 2014, 35(6): 1199.

图/表 3

Table 1 Experimental conditions and results of tolualdehyde ultrasonic electrosythesis

No.	c/(mol·L^-1)	I/A	V/mL	Mass fraction(%)			τ(%)
No.	c/(mol·L^-1)	I/A	V/mL	o-T		m-T	p-T
1	3.3	0.65	2.50	14.55	4.94	80.51	20.02
2	3.6	0.77	4.25	16.98	9.34	73.68	54.02
3	3.9	0.89	2.25	17.97	10.94	71.09	25.91
4	4.2	0.56	4.00	16.82	8.04	75.14	65.78
5	4.5	0.68	2.00	20.24	10.57	69.19	29.00
6	4.8	0.80	3.75	16.88	8.43	74.69	65.98
7	5.1	0.92	1.75	20.27	12.12	67.61	27.24
8	5.4	0.59	3.50	14.47	5.87	79.66	53.04
9	5.7	0.71	1.50	18.23	8.78	72.99	29.25
10	6.0	0.83	3.25	12.95	5.90	81.14	33.38
11	6.3	0.95	1.25	20.63	12.71	66.66	18.25
12	6.6	0.62	3.00	0	6.24	93.76	13.14
13	6.9	0.74	1.00	25.78	24.92	49.30	15.56
14	7.2	0.86	2.75	3.15	5.19	91.65	13.64
15	7.5	0.98	4.50	0	6.17	94.56	8.08

Fig.1 Prediction value of experiment results under different conditions(A1—A4) V=2.0 mL; (B1—B4) V=3.0 mL; (C1—C4) V=4.0 mL.

Table 2 Prediction and verification of experimental results

Content	Prediction condition			Prediction result				Determination result
Content	c/(mol·L^-1)	I/A	V/mL	W_o_-T(%)	W_m_-T(%)	W_p_-T(%)	τ(%)	W_o_-T(%)	W_m_-T(%)	W_p_-T(%)	τ(%)
$W p - T$ (%)	7.55	0.87	2.89	4.67	5.33	90.01	15.88	4.69	4.21	91.10	14.97
$W p - T$ + $W o - T$ (%)	6.07	0.82	2.90	12.65	6.95	80.38	27.58	15.20	4.86	79.91	29.01
τ(%)	4.64	0.79	3.85	16.80	8.43	74.77	67.00	17.20	8.49	74.31	68.03

Table 2 Prediction and verification of experimental results

Content	Prediction condition			Prediction result				Determination result
Content	c/(mol·L^-1)	I/A	V/mL	W_o_-T(%)	W_m_-T(%)	W_p_-T(%)	τ(%)	W_o_-T(%)	W_m_-T(%)	W_p_-T(%)	τ(%)
$W p - T$ (%)	7.55	0.87	2.89	4.67	5.33	90.01	15.88	4.69	4.21	91.10	14.97
$W p - T$ + $W o - T$ (%)	6.07	0.82	2.90	12.65	6.95	80.38	27.58	15.20	4.86	79.91	29.01
τ(%)	4.64	0.79	3.85	16.80	8.43	74.77	67.00	17.20	8.49	74.31	68.03

参考文献 19

[1]	Gao J., Arpngicial Neural Networks and Simulation(Second Edition), Machine Industry Press, Beijing, 2007, 1—20
	(高隽. 人工神经网络原理及仿真实例(第二版), 北京: 机械工业出版社, 2007, 1—20)
[2]	Lei Y.J., Zhang S. W., Li X. W., Zhou C. M., MATLAB Genetic Algorithm Toolbox and Its Application, Xidian University Press, Xi'an, 2005, 1—3
	(雷英杰, 张善文, 李续武, 周创明. MATLAB遗传算法工具箱及应用, 西安: 西安电子科技大学出版社, 2005, 1—3)
[3]	Zhang Q. Y., Zhang D. D., Suo J. J., Li J. Y., Long H. L., Xu L., Chem. J. Chinese Universities, 2012, 33(7), 1413—1419
	(张庆友, 张丹丹, 索静洁, 李静亚, 龙海林, 许禄.高等学校化学学报, 2012,33(7), 1413—1419)
[4]	Wang L. L., Zhang J., Liu H. Y., Zhang H. T., Wang H. Y., Yang X. R., Wang Y. H., Chem. Res. Chinese Universities, 2010, 26(6), 899—904
[5]	Zhao T. Q., Meng F. Y., Wang H. Y., Gao Y., Chem. Res. Chinese Universities, 2012, 28(5), 802—806
[6]	Fauzi A. H. M., Amin N. A. S., Energy Convers. Manage., 2013, 76, 818—827
[7]	Fauzi A. H. M., Amin N. A. S., Mat Ramli M., Appl. Energy, 2014, 114, 809—818
[8]	Tao Y., Wu D., Zhang Q. A., Sun D. W., Ultrason. Sonochem., 2014, 21, 706—715
[9]	Hassan G., Zahra D., Acree Jr. W. E., J. Solution Chem., 2013, 42(2), 338—357
[10]	Fu X. H., Hong X. D., Liu S. D., Ye Y. F., Rong Y. C., Chen X. L., Ren B., Chin. Pharm. J., 2013, 48(12), 1000—1004
	(傅晓华, 洪晓丹, 刘石带, 叶毅芳, 容颖慈, 陈小陆, 任斌.中国药学杂志, 2013,48(12), 1000—1004)
[11]	Martínez-Morales J. D., Palacios-Hernández E. R., Velázquez-Carrillo G. A., J. Zhejiang Univ. Sci. A, 2013, 14(9), 657—670
[12]	Chen Q. S., Zhang Y. H., Zhao J. W., Hui Z., Anal. Methods, 2013, 5, 6382—6388
[13]	Sanchooli M., Ghaffari M. M., Zangeneh M., Res. J. Chem. Environ., 2013, 17(5), 32—40
[14]	Toubaei A., Golmohammadi H., Dashtbozorgi Z., Acree W. E. Jr., J. Mol. Liq., 2012, 175, 24—32
[15]	Xu K.X., Handbook of Fine Organic Chemical Raw Materials and Intermediates, Chemical Industry Press, Beijing, 1998, 3—155
	(徐克勋. 精细有机化工原料及中间体手册, 北京: 化学工业出版社, 1998, 3—155)
[16]	Kan X. W., Tao H. S., Du J., Zhou Y. Y., Fang B., Chin. J. Org. Chem., 2003, 23(11), 1282—1285
	(阚显文, 陶海升, 杜俊, 周运友, 方宾.有机化学, 2003,23(11), 1282—1285)
[17]	Lindermeir A., Horst C., Hoffmann U., Ultrason. Sonochem., 2003, 10(4—5), 223—229
[18]	Yi Q. F., Yu Z. L., Fan M., Zhou X. L., Liu X. P., Chin. J. Appl. Chem., 2005, 22(10), 1127—1131
	(易清风, 于站良, 范敏, 周秀林, 刘小平.应用化学, 2005,22(10), 1127—1131)
[19]	Tang G. Y., Wu H. J., Chin. J. Chromatogr., 1993, 11(1), 43, 68
	(唐根源, 吴红京. 色谱, 1993, 11(1), 43, 68)