基于神经网络和遗传算法的池塘溶解氧预测模型

A prediction model for dissolved oxygen level in a fish pond based on combination of neural network and genetic algorithm

水产养殖池塘是一个多变量、非线性和大时延系统,其中溶解氧的预测也是一个复杂的问题。针对大连某水产养殖池塘,作者建立了一个基于Levenberg-Marquardt(LM)神经网络和遗传算法(GA)的溶解氧预测模型GA-LM,并将该模型与传统的BP神经网络进行比较分析。结果表明:使用本研究中建立的GA-LM模型预测的溶解氧值和实际测定值吻合较好,预测更为精准,运行时间明显减少。

The prediction of dissolved oxygen （DO） level is complicated in aquaculture ponds as a complex system with multi-variables, nonlinearity and long-time lag. In this study, GA-LM, a hybrid neural network model com- bining Levenberg Marquardt（LM） algorithm and Genetic Algorithm （GA） was developed for DO level predicting in an aquaculture pond at Dalian, China. The The comparison of performance of GA-LM with the conventional Back -Propagation （BP） algorithm revealed that the predicted DO values using GA-LM model are in good agreement with the measured data, indicating that the model is capable of predicting DO accurately and rapidly.