摘要
海参具有极高的营养价值和药用价值,水质环境对其产量有一定的影响。为了更好地调控水质,尽可能使海参生长在最佳状态,采用改进的小波降噪方法处理数据,建立长短期记忆(LSTM)神经网络模型对海参养殖环境中的氨氮浓度进行预测。实验分别采用多影响因素作为模型的输入,氨氮浓度作为输出,建立氨氮浓度与各水质因子之间的关系模型,实现氨氮浓度预测。实验结果表明,改进的小波降噪方法有效减少了噪声,LSTM神经网络模型在海参养殖水质预测中效果显著。所提方法为海参养殖下一步水质调控提供了参考数据,进而可提高海参养殖的质量和产量。
Sea cucumber has very high nutritional value and medicinal value,and water environment has a certain influence on its yield.In order to better control water quality and make sea cucumber grow in the best condition,an improved wavelet denoising method is used to process data in this paper,and a long short-term memory(LSTM)neural network model is established to predict ammonia nitrogen concentration in sea cucumber aquaculture environment.In the experiment,multiple influencing factors are used as the input of the model,and ammonia nitrogen concentration is used as the output.The relationship model of ammonia nitrogen concentration and various water quality factors is established to realize the prediction of ammonia nitrogen concentration.The experimental results show that the improved wavelet denoising method can effectively reduce noise,and the LSTM neural network model has a significant effect in the prediction of water quality for sea cucumber aquaculture.The proposed method provides reference data for the water quality control of sea cucumber aquaculture in the next step,and then improves the quality and yield of sea cucumber aquaculture.
作者
李先鹏
吴若男
王魏
李双双
LI Xian-peng;WU Ruo-nan;WANG Wei;LI Shuang-shuang(College of Information Engineering,Dalian Ocean University,Dalian 116023,China;Dalian Xinyulong Marine Biological Seed Technology Co.,Ltd.,Dalian 116000,China)
出处
《控制工程》
CSCD
北大核心
2022年第4期587-592,626,共7页
Control Engineering of China
基金
辽宁省教育厅青年科技人才“育苗”项目(QL201912)
大连市科技之星项目(2017RQ143)。
关键词
海参养殖
LSTM
小波降噪
氨氮浓度预测
Sea cucumber aquaculture
LSTM
wavelet denoising
ammonia nitrogen concentration prediction