基于WT-CNN-LSTM的溶解氧含量预测模型  

Dissolved Oxygen Prediction Model Based on WT-CNN-LSTM

作　　者：陈英义[1,2] 方晓敏 梅思远 于辉辉 杨玲 CHEN Yingyi;FANG Xiaomin;MEI Siyuan;YU Huihui;YANG Ling(College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;Key Laboratory of Agricultural Information Acquisition Technology,Ministry of Agriculture and Rural Affairs,Beijing 100083,China;National Digital Fishery Innovation Center,Beijing 100083,China;College of Information,Beijing Forestry University,Beijing 100083,China)

机构地区：[1]中国农业大学信息与电气工程学院,北京100083 [2]农业农村部农业信息获取重点实验室,北京100083 [3]国家数字渔业创新中心,北京100083 [4]北京林业大学信息学院,北京100083

出　　处：《农业机械学报》2020年第10期284-291,共8页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家重点研发计划项目(2017YFE0122100);山东省重点研发计划项目(2017CXGC0201)。

摘　　要：溶解氧(Dissolved oxygen,DO)含量是影响水产养殖产量的重要因素之一,具有时序性、不稳定性和非线性等特点,且其影响因子过多、存在复杂的耦合关系,难以实现精准预测。针对传统长短时记忆神经网络(Long short-term memory,LSTM)预测模型易引入冗余数据,且在训练过长序列时会出现梯度消失现象,从而不能捕捉因子间长期的依赖性问题,提出了基于小波变换(Wavelet transform,WT)、卷积神经网络(Convolutional neural network,CNN)和LSTM的溶解氧含量预测模型。首先,使用WT降低数据噪声;然后,使用CNN深度挖掘各变量之间的潜在关系;最后,利用LSTM的时序性预测2 h后的水产养殖溶解氧含量。结果表明,本文提出的WTCNNLSTM模型预测效果良好,其平均绝对误差、均方根误差和决定系数分别为0.138、0.229和0.954,比传统LSTM模型分别优化了28.87%、21.03%和4.61%。Dissolved oxygen(DO)plays an important role in aquaculture.It has the characteristics of changing with time,instability and nonlinearity,and it has too many influence factors with complex coupling relationship,and it is difficult to be predicted accurately.The traditional long short-time memory neural network(LSTM)is easy to introduce redundant data.And when it deals with long sequences,the gradient disappears so that it cannot capture very long term dependencies.To solve the problems above,the WTCNNLSTM prediction model was proposed.In view of the timing and nonlinearity of dissolved oxygen in aquaculture,the LSTM,which was widely used in time series prediction and had excellent performance,was selected to predict the dissolved oxygen value in two hours later.Aiming at the noise generated by environmental factors,human factors and system factors in the process of data collection,the hybrid wavelet transform(WT)was proposed to reduce noise in the data set so as to provide reliable support for the establishment of accurate prediction model.Moreover,due to the complex aquaculture environment,the dissolved oxygen content was affected by a variety of water quality factors and environmental factors.Therefore,the convolutional neural network(CNN)was used to mine and store the potential information between variables and DO in aquaculture.The result showed that WTCNNLSTM had good predictive performance.Its mean absolute error,root mean squared error and determination coefficient were 0.138,0.229 and 0.954,respectively,which were optimized by 28.87%,21.03%and 4.61%compared with those of the LSTM model.

关 键 词：溶解氧 预测模型 小波变换 卷积神经网络 长短时记忆神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]