Mathematical Modeling and Neural Network Control for Dissolved Oxygen of Aquaculture Pond Aeration System

Dissolved oxygen (DO) is considered as one of the most important aspect of aquaculture. It is needed by fish to respire and perform metabolic activities. Thus low levels of dissolved oxygen are often linked to fish kill incidents. On the other hand, optimum levels can result to good growth, thus result to high production yield. To increase pond production it is necessary to control dissolved oxygen. Artificial intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques or as components of integrated systems. They have been used to solve complicated practical problems in various areas and are becoming more and more popular nowadays. This paper presents a new design of diffused aeration system using fuel cell as a power source. Mathematical modeling of dissolved oxygen presents in the pond over the day and the fuel cell stack modeling are also presented. Artificial intelligence control techniques are used for controlling the speed of air flow rate from the blower to air piping connected to the pond through control blower speed. MATLAB SIMULINK results show the neural network control (NNC) offer high performance of the system. Keyword: aeration system, fuel cell, artificial intelligence (AI) techniques, neural network control.