School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, 510006, China.
School of Mathematics and information science, Guangzhou University, Guangzhou, 510006, China.
Math Biosci Eng. 2019 Apr 10;16(4):2990-3002. doi: 10.3934/mbe.2019148.
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.
增氧机是水产养殖中不可或缺的工具，而中国是世界上最大的水产养殖国之一。因此，增氧机的智能控制对于节能、环保和防止溶解氧恶化具有重要意义。在实践和研究中，还没有与智能增氧机相关的工作。在本文中，我们主要研究基于深度学习的智能增氧机控制，并提出了一种基于长短期记忆网络的溶解氧预测算法，简称 DopLSTM。将预测结果用于增氧机的智能控制设计。结果表明，增氧机的智能控制可以有效降低功耗，防止溶解氧恶化。
