电子科技2024，Vol.37Issue(4)：87-96,10.DOI:10.16180/j.cnki.issn1007-7820.2024.04.012
基于ISSA-LSTM的黄鳝池溶氧量多参数预测
Multi-Parameter Prediction of Dissolved Oxygen in Eel Ponds Based on ISSA-LSTM
摘要
Abstract
In order to improve the multi-parameter prediction accuracy of dissolved oxygen,an ISSA-LSTM(Improved Sparrow Search Algorithm-Long and Short-Term Memory Neural Networks)dissolved oxygen prediction model is developed based on the ISSA and LSTM.The model is applied to the prediction of dissolved oxygen in eel breeding ponds at Shanghai academy of agricultural sciences.The sparrow search algorithm is optimized using chaos mapping,lensing imaging backward learning,adaptive adjustment and Cauchy variation.The data are pre-pro-cessed by wavelet transform,the input parameters for model training are determined using principal component analy-sis.The training results show that the correlation coefficient,root mean square error,mean square error and mean absolute error are 0.911,1.392 mg·L-1,1.938 mg·L-1 and0.992 mg·L-1,which are all better than those in the control model.The choice of model input parameters also have an impact on the model prediction results,with the best model predictions using both moderately and strongly correlated parameters with dissolved oxygen as input param-eters.The training results provide a new perspective for the development of the dissolved oxygen multi-parameter prediction model.关键词
溶氧量预测/长短期记忆神经网络/麻雀搜索算法/主成分分析法/小波变换/柯西变异/混沌映射/黄鳝养殖Key words
dissolved oxygen prediction/long and short-term memory neural networks/sparrow search algo-rithm/principal component analysis/wavelet transform/Cauchy variation/chaos mapping/eel farming分类
信息技术与安全科学引用本文复制引用
林彬彬,徐震,袁泉,田志新..基于ISSA-LSTM的黄鳝池溶氧量多参数预测[J].电子科技,2024,37(4):87-96,10.基金项目
国家农业环境奉贤观测实验站项目(NAES035AE03) （NAES035AE03）
上海市科技兴农项目(2022-02-08-00-12-F01186)National Agricultural Environment Fengxian Observation Experiment Station Project(NAES035AE03) （2022-02-08-00-12-F01186）
Shanghai Science and Technology for Rural Development Project(2022-02-08-00-12-F01186) （2022-02-08-00-12-F01186）
