应用人工神经网络评价长春南湖水的营养状态

根据水质分析资料，以化学需氧量，总氮和总磷作为评价参数，经过反复的尝试，构建了具有４层结构用于评价湖泊的营养状态的误差逆传播网络，其输入层有３个神经元，２个隐含层各有４个神经元，输出层有１个神经元，将湖泊营养状态评价标准作为样本模式提供给网络，按照误差逆传播网络的学习规则对网络进行训练，经过３９９２５次学习后网络达到预先给定的收敛标准，应用该网络对长春南湖水的营养状态进行了评价，操作过程简便易行，

Artificial Neural Network Evaluation of Nutrient States of South Lake Water in Changchun

Artificial neural network was developed to evaluate the nutrient states of South Lake water in Changchun in this paper. Taking Chemical Oxygen Demand, Tolal Nitrogen and Total Phosphorus as evaluation parameters and after repeating attempts, the four layer structural Error Back Propagation network was established to evaluate lake nutrient states.There are three neural units in input layer, four in both hidden layers, and one in output layer. Taking the evaluation criterion of lake nutrient states as sample pattern, the network was trained in the light of learning rule of Error Back Propagation network. After 39?925 tries, the network reached the convergence standard given in advance. The operation process of the network is simple and convenient, and the results indicate that South Lake water in Changchun is, on the whole, in the state of extreme eutrophication.