摘要
东江惠州－东岸段河流水质直接影响着香港和深圳的淡水供应质量.本文根据东江水质自动监测系统的分布情况，提出了由上游水质预测下游水质和当前水质预测未来水质的两种基于自适应神经网络的东江惠州－东岸段水质预测建模方法，给出了基于正交多项式基的神经网络静、动态学习算法，在学习过程中可同时确定网络的拓扑结构和相应的正交多项式基，且无局部极值问题。仿真结果证明了该方法具有较高的预测精度，且方法简便、适用对象广泛。
Two adaptive neural network based predictive models of water quality for a river reach are put forward. One is that anticipating the lower course water quality by measuring the upriver water quality. Another is that estimating the future state with current water quality in a same position. The learning algorithms with orthogonal basis transfer function for static and dynamic neural networks are provided. Both the neuron numbers and orthogonal basis transfer function can be established automatically in training process. The local extremum problem does not exist in the method. Simulation results prove that the proposed approaches have high precision, good adaptability and extensive applicability.
出处
《系统仿真学报》
EI
CAS
CSCD
2001年第2期139-142,209,共5页
Journal of System Simulation
基金
国家自然科学基金!(69874005)
广东省环保局项目!(980010)
关键词
神经网络
水质预测
河流水质
环境监测
数学模型
neural network
water quality prediction
orthogonal basis transfer function
