基于人工神经网络和遗传算法研究锰过氧化酶脱色甲基橙

基于锰过氧化物酶(MnP)氧化脱色偶氮类染料的原理,实验研究MnP对甲基橙的脱色工艺,采用人工神经网络(ANN)和遗传算法(GA)建立脱色模型并优化工艺。建立的ANN模型的误差、相关系数、均方根误差和绝对平均偏差分别为0.0009、0.9971、1.21和6.82,模型有效且能够用于预测和工艺优化。采用GA对ANN模型进行数值寻优,得到的最佳工艺条件为酶液量0.6 mL,Mn2+浓度4 mmol/L,H2O2浓度0.49 mmol/L。该条件下脱色率达到(90.74±0.59)%。ANN耦合GA有效地建立了锰过氧化物酶脱色甲基橙的模型,并优化了工艺参数,为甲基橙脱色的研究提供一定参考。

Coupling of artificial neural network and genetic algorithms for methyl orange decolorization with manganese peroxidase

On the basis of mechanism of azo dyes decolorization with manganese peroxidase, mathematical model and technical conditions of methyl orange decolorization with manganese peroxidase were investigated by artificial neural network and genetic algorithms. The error, correlation coefficient determination, root mean square error and absolute average deviation of the established model through artificial neural network were 0.0009, 0.9971, 1.21 and 6.82, respectively. Moreover, the optimum conditions of decolorization through genetic algorithms were MnP of 0.6 mL, Mn²⁺ concentration of 4 mmol/L and H₂O₂ concentration of 0.49 mmol/L, for the maxmium decolorization of (90.74±0.59)%. Results suggest that the coupling of artificial neural network and genetic algorithms is an effective technique for the investigation of methyl orange decolorization with manganese peroxidase. These results are references for researches on technique of methyl orange decolorization.