摘要
在水产养殖当中,水质数据的实时性和精确性对养殖活动具有重要作用。除从物理层面提高水质监测系统准确性外,对所获水质数据使用算法优化处理,可大幅提高数据的精确性。运用神经网络辅助卡尔曼滤波算法对水质监测数据进行处理,能够将溶解氧的平均绝对误差降低27%以上,均方误差降低39%以上,均方根误差降低22%以上,对pH的平均绝对误差也可以降低20%以上。精确的水质数据为养殖户的科学水产养殖提供了数据支撑。
In aquaculture,the real-time and accuracy of water quality data play an important role in aquaculture activities.In addition to improving the accuracy of the water quality monitoring system from the physical level,the use of algorithm optimization processing for the obtained water quality data can greatly improve the accuracy of the data.This design uses the neural network-assisted Kalman filter algorithm to process the water quality monitoring data,which can reduce the average absolute error of dissolved oxygen by more than 27%,the mean square error by more than 39%,and the root mean square error by more than 22%.The mean absolute error of pH value can also be reduced by more than 20%.Accurate water quality data provides data support for farmers' scientific aquaculture.
作者
李凯林
孟繁朴
任万龙
郝宗睿
LI Kailin;MENG Fanpu;REN Wanlong;HAO Zongrui(Institute of Oceanographic Instrumentation,Qilu University of Technology(Shandong Academy of Sciences),Qingdao 266100,China)
出处
《齐鲁工业大学学报》
CAS
2023年第5期28-33,共6页
Journal of Qilu University of Technology
基金
山东省重大科技创新工程项目(2019JZZY010819)。
关键词
水质监测
神经网络
卡尔曼滤波
water quality monitoring
neural network
Kalman filtering
