摘要
溶解氧浓度作为水质检测的重要指标,在环境监测、食品加工、电力电子等行业具有重要的应用。采用基于遗传算法优化的极限学习机算法,建立了电极长度和传感器的输出电流、响应时间之间关系的预测模型,优化了阳极与电解液的接触面积,验证了传感器的测量稳定性和精度。结果表明,当阳极与阴极的反应面积之比约为33时,传感器的残余电流小于0.2μA,上升和下降响应时间均小于60s;重复5次的实验结果表明,自制传感器具有较好的稳定性;与商用传感器相比,自制传感器测量的相对误差小于1%,表明其具有较高的测量精度。
As a key indicator of water quality testing,dissolved oxygen concentration has important applications in environmental monitoring,food processing,electrical power,electronics and other industries.Using an extreme learning machine algorithm based on genetic algorithm optimization,a model for predicting the relationship between the electrode length,output current and response time of a self-made sensor has been established.The contact area between the anode and electrolyte was optimized,and the measurement stability and accuracy of the self-made sensor were verified.The results showed that when the ratio of the reaction area of the anode to cathode is about 33,the residual current of the sensor is less than 0.2μA,and the rising and falling response time is less than 60 s.When the experiment was repeated five times,the results showed that self-made sensor has good stability.Compared with the commercial sensor,the measurement error of the self-made sensor is less than 1%,which indicates that it has high measurement accuracy.
作者
郑志城
陈娟
ZHENG ZhiCheng;CHEN Juan(College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China)
出处
《北京化工大学学报（自然科学版）》
CAS
CSCD
北大核心
2021年第2期117-123,共7页
Journal of Beijing University of Chemical Technology(Natural Science Edition)
基金
国家自然科学基金(61771034)。
关键词
电极
溶解氧
遗传算法
极限学习机回归
误差分析
electrode
dissolved oxygen
genetic algorithms
extreme learning machine regression
error analysis
