基于神经网络模型的城市生活垃圾预测
Forecast of Urban House Refuse Based on Neural Network Model
-
摘要: 研究了城市生活垃圾清运量的预测问题．先用模糊聚类分析法对影响城市垃圾清运量产生的因素进行分类，然后按照一定的准则筛选出影响城市垃圾清运量产生的主要因素，以此确定神经网络模型的输入变量，建立起城市生活垃圾清运量BP神经网络预测模型．经过训练之后的网络，平均绝对百分误差为4.94％，达到了高精度拟合；以此训练好的神经网络模型预测了深圳市2013-2015年的生活垃圾清运量，分别达528.36，535.28，541.79万吨．Abstract: Living garbage freight volume forecasting problems of the city has been studied in this paper by means of fuzzy cluster analysis to classify the factors w hich influence the city garbage removal amount ,and then some rules used to screen the major factors to determine the input variable of neural network model to establish BP neural network forecast model of city garbage removal amount .After the network is trained , its mean absolute percentage error is 4 .94% ,and this achieves the high precision fitting .With this trained neural network model ,we forecast that the living garbage disposal of Shenzhen from 2013 to 2015 will be 528 .38 tons ,535 .28 tons ,541 .79 tons .
-
-
计量
- 文章访问数: 497
- HTML全文浏览数: 352
- PDF下载数: 0
- 施引文献: 0
下载: