摘要
为准确掌握水产养殖中重要水质参数氨氮的变化趋势,提出了基于PCA-NARX神经网络的氨氮预测模型,用主成分分析法提取的主成分变量作为网络输入,优化网络结构,以中华绒螯蟹Eriocheir sinensis的养殖水体为例,建立了PCA-NARX网络模型,并与NAR、NARX网络模型进行了对比试验。结果表明:PCA-NARX模型在24 h和48 h内均方根误差(RMSE)最小,较NAR网络模型减少24. 39%,较NARX网络模型减少41. 94%;总体在48 h之内,PCA-NARX网络模型相对于NAR、NARX网络模型具有更好的泛化能力,对氨氮的预测性能较好。本试验结果可为中华绒螯蟹养殖水体的氨氮调控提供参考依据。
An ammonia nitrogen level forecasting model is developed based on the PCA-NARX neural network in which principal component variables extracted are used as exogenous inputs by principal component analysis(PCA)and the network structure was optimized in order to improve accuracy of ammonia nitrogen level forecasting and grasp the trend of the ammonia nitrogen levels accurately.The forecasting performance was conducted in a Chinese mitten handed crab Eriocheir sinensis tank compared with NAR and NAR neural networks.Simulation results show that the proposed method has good nonlinear fitting ability and its root mean square error(RMSE)is lower than that in NAR and NARX in24h,consistent with NAR and NARX in24h and48h.Also,the comparison with other models indicates that PCA-NARX neural network has better nonlinear fitting ability and superior in forecasting dissolved oxygen level based on the RMSE in short term(48h),and can be used to offer scientific guidance to control water quality.
作者
袁红春
赵彦涛
刘金生
YUAN Hong-chun;ZHAO Yan-tao;LIU Jin-sheng(College of Information Technology,Shanghai Ocean University,Shanghai 201306,China;College of Fisheries and Life Science,Shanghai Ocean University,Shanghai 201306,China)
出处
《大连海洋大学学报》
CAS
CSCD
北大核心
2018年第6期808-813,共6页
Journal of Dalian Ocean University
基金
国家自然科学基金资助项目(41776142)
关键词
氨氮预测
PCA-NARX神经网络
主成分分析
水产养殖
ammonia nitrogen level forecasting
PCA-NARX neural network
principal component analysis
aquaculture
