模糊方法改进的反向传输神经网络预测南美白对虾养殖的水质  

Penaeus vannamei aquaculture water quality prediction based on the improved back propagation neural network

作　　者：丁金婷[1] 臧泽林[1] 黄敏[1] 

机构地区：[1]浙江大学城市学院信息与电气工程学院,杭州310015

出　　处：《浙江大学学报（农业与生命科学版）》2017年第1期128-136,共9页Journal of Zhejiang University:Agriculture and Life Sciences

基　　金：浙江省重大科技专项(2012C03009-2);杭州市科技发展计划项目(20140432B08)

摘　　要：在南美白对虾高密度、规模化围塘养殖生产中,水质参数的监测、评价及预警是至关重要的。以杭州市某南美白对虾基地日常养殖水质为研究对象,选取温度、pH值、溶解氧、氧化还原电位等4项指标作为预测参数,建立拓扑结构为40-14-4的3层前馈反向传输(back propagation,BP)神经网络模型,即以连续10个时间单位的预测变量为输入层,隐含层节点数为14个,输出层变量为温度、pH值、溶解氧和氧化还原电位。为克服传统BP神经网络存在的收敛速度慢、易陷入震荡和泛化能力不强等缺点,采用模糊方法优化了自适应变步长BP神经网络算法,缩短了BP神经网络的训练时间,提高了网络收敛效率与稳定度。结果表明,以模糊方法改进的BP神经网络(FABPM)方法具有收敛速度快、预测精度高、稳定度好等特点,对选取的4项水质指标都给出了较好的训练与预测结果,预测的平均相对误差小于2.5%,从而为水产养殖水质预测与评价提供了一种新方法。Penaeus vannamei is one of the important commercial species in the shrimp farming industry in China in virtue of its wide range of feeding,rapid growth,strong environmental tolerance and disease resistance,etc.In recent years,deteriorating water quality has caused massive financial losses to farmers,which has become one of the major bottlenecks to production output and the minimization of disruptions to production processes.In addition,with the development of aquaculture,the culture environment and water quality have been degraded greatly because of the waste-water drainage.The monitoring,evaluation and early warning of the water quality parameters in intensive and large-scale P.vannamei tanks are key areas to be considered in aquaculture development.According to the water quality monitoring data from one of the P.vannamei breeding base in Hangzhou,a mathematical model of multi-layer feed forward neural network was established to predict and evaluate the quality of aquaculture water.The topology of the model was 40-14-4,that was,the temperature,pH value,dissolved oxygen,and oxidation-reduction potential were the input variables in m=10consecutive time units,the number of hidden layer nodes was 14,and the output layer was 4.In order to overcome the disadvantages of traditional back propagation（BP）neural network including slow convergence speed,easy to fall into the shock,poor generalization ability and so on,the adaptivevariable step size BP-neural network learning algorithm based on the fuzzy method had been developed,which can reduce the learning time of BP-neural network,improve the convergence efficiency and network stability.The computed results for water quality showed good agreement with the measured values.The correlation coefficients for the temperature,pH value and the oxidation-reduction potential during the training and testing processes were better than 0.975.The comparison between the original measured and predicted values of the BPneural network showed that the relative errors,with a few excepti

关 键 词：南美白对虾 水质预测 反向传输神经网络 模糊自适应变步长算法 

分 类 号：TP3-05[自动化与计算机技术—计算机科学与技术]