Deep learning-based intelligent precise aeration strategy for factory recirculating aquaculture systems

• Published in: Artificial intelligence in agriculture Vol. 12; pp. 57 - 71
• Main Authors: Yang, Junchao, Zhou, Yuting, Guo, Zhiwei, Zhou, Yueming, Shen, Yu
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2024; KeAi Communications Co., Ltd
• Subjects: Deep learning; Intelligent control; Precise aeration; Recirculating aquaculture system; Deep learning; Precise aeration; Recirculating aquaculture system; Intelligent control
• ISSN: 2589-7217; 2589-7217
• DOI: 10.1016/j.aiia.2024.04.001

Factory recirculating aquaculture system (RAS) is facing in a stage of continuous research and technological innovation. Intelligent aquaculture is an important direction for the future development of aquaculture. However, the RAS nowdays still has poor self-learning and optimal decision-making capabilities, which leads to high aquaculture cost and low running efficiency. In this paper, a precise aeration strategy based on deep learning is designed for improving the healthy growth of breeding objects. Firstly, the situation perception driven by computer vision is used to detect the hypoxia behavior. Then combined with the biological energy model, it is constructed to calculate the breeding objects oxygen consumption. Finally, the optimal adaptive aeration strategy is generated according to hypoxia behavior judgement and biological energy model. Experimental results show that the energy consumption of proposed precise aeration strategy decreased by 26.3% compared with the manual control and 12.8% compared with the threshold control. Meanwhile, stable water quality conditions accelerated breeding objects growth, and the breeding cycle with the average weight of 400 g was shortened from 5 to 6 months to 3–4 months. •Aeration solution for recirculating aquaculture system based on computer vision.•Real time monitoring of the health status of breeding objects based on deep learning.•Precision aeration control using multi-source data model enhances accuracy.•Experimental demonstration under real recirculating aquaculture scenario.