摘要
针对传统BP模型存在着训练速度较慢、局部极值以及最佳网络结构无法准确确定的不足 ,进行了改进 ,应用于城市空气污染预报 ,建立大气污染浓度的神经网络预测模型。计算结果表明 ,应用改进的BP模型进行大气污染预报能够得到更好的预测结果 。
According to the deficiency of traditional BP model in the slow training speed, the local minimum and the uncertainty on the best structure of neural network, BP model is improved and applied to urban atmospheric pollution prediction.A neural network prediction model of atmospheric pollutant concentration is set up. The results have showed that higher prediction precision and the efficient utility can be achieved by using improved BP model.
出处
《城市环境与城市生态》
CAS
CSSCI
CSCD
北大核心
2002年第5期17-19,共3页
Urban Environment & Urban Ecology
关键词
BP模型
大气污染预报
人工神经元网络
遗传算法
artificial neural network
BP model
atmospheric pollution prediction
Genetic Algorithm (GA)
