期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：267
期号：3
页码：1-8
DOI：10.1088/1755-1315/267/3/032075
出版社：IOP Publishing
摘要：In order to understand the changes of water quality in the water, the paper uses the improved BP network of LM algorithm to learn and train the data, and implements the neural network model on the MATLAB platform, and uses the processed samples for the established BP neural network. Learning training, in order to prevent some neurons from reaching the state of supersaturation.By normalizing the data, the trained network is used to predict the water quality indicators of the Luanhe River Line. The results show that it is feasible to evaluate the water quality along the sputum by BP neural network model. The model has strong learning, association and fault tolerance functions. The analysis results and process are close to the thinking process and analysis method of the human brain, which makes the water quality evaluation. The accuracy of the results is greatly improved.
