响应面法与GA-BP神经网络联合优化细菌降解石油烃参数研究  

Parameter optimization for bacterial degradation of petroleum hydrocarbons by response surface methodology and GA-BP neural network jointly

作　　者：鲁钧豪 孙先锋[1] 王致桦 宋柯 吴蔓莉[2] LU Jun-hao;SUN Xian-feng;WANG Zhi-hua;SONG Ke;WU Man-li(School of Environmental and Chemical Engineering,Xi’an Polytechnic University,Xi’an 710048,China;School of Environmental and Municipal Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,China)

机构地区：[1]西安工程大学环境与化学工程学院,陕西西安710048 [2]西安建筑科技大学环境与市政工程学院,陕西西安710055

出　　处：《现代化工》2025年第4期102-109,共8页Modern Chemical Industry

基　　金：国家自然科学基金项目(52070154);陕西省科技厅重点研发计划项目(2023-YBNY-251)。

摘　　要：采用单因素法考察环境因子对石油烃降解率的影响,以石油烃降解率为响应值,利用响应面法(RSM)和遗传算法优化反向传播(GA-BP)神经网络和石油烃降解条件,并对优化结果进行对比。结果表明,目标菌株BM-1为蕈状芽孢杆菌(Bacillus mycoides),经GA-BP神经网络优化后的最优降解条件为:温度为35.10℃、pH为7.96、菌液接种量为5.17%、初始原油质量分数为1.02%,该条件下石油烃降解率的试验值可达(63.15±0.73)%,而GA-BP神经网络的预测值为63.4926%,预测值与试验值之间相对误差仅0.54%,模型整体拟合度较高(R=0.976 06),说明应用GA-BP神经网络优化石油烃降解条件合理可行。The effects of environmental factors on the degradation rate of petroleum hydrocarbons are investigated by using a single-factor method.Taking the degradation rate of petroleum hydrocarbons as the response value,the conditions for petroleum hydrocarbon degradation are optimized through using response surface methodology(RSM)and genetic algorithm-optimized back propagation(GA-BP)neural network jointly,and the optimization results are compared.Results show that the target strain BM-1 is Bacillus mycoides.The optimal degradation conditions obtained after GA-BP neural network optimization are as follows:temperature is 35.10℃,pH is 7.96,the inoculation amount of bacterial solution is 5.17%,and initial crude oil concentration is 1.02%.Under these conditions,the experimental degradation rate of petroleum hydrocarbons reaches 63.15±0.73%,while the predicted value given by GA-BP neural network is 63.4926%,with a relative error of only 0.54%between the predicted and experimental values.The model demonstrates a high degree of fit(R=0.97606),indicating that the application of GA-BP neural network optimization for petroleum hydrocarbon degradation conditions is reasonable and feasible.

关 键 词：石油烃降解 响应面法 条件优化 GA-BP神经网络 

分 类 号：X53[环境科学与工程—环境工程] Q89[生物学]