Open AccessAn intelligent aerator algorithm inspired-by deep learning
Author(s) -
Hongjie Deng,
Lingxi Peng,
Zhang Jia-jing,
Chunming Tang,
Haoliang Fang,
Haohuai Liu
Publication year - 2019
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2019148
Subject(s) - computer science , artificial intelligence , aeration , algorithm , machine learning , ecology , biology
Aerator is an indispensable tool in aquaculture, and China is one of the largest aquaculture countries in the world. So, the intelligent control of the aerator is of great significance to energy conservation and environmental protection and the prevention of the deterioration of dissolved oxygen. There is no intelligent aerator related work in practice and research. In this paper, we mainly study the intelligent aerator control based on deep learning, and propose a dissolved oxygen prediction algorithm with long and short term memory network, referred as DopLSTM. The prediction results are used to the intelligent control design of the aerator. As a result, it is proved that the intelligent control of the aerator can effectively reduce the power consumption and prevent the deterioration of dissolved oxygen.