Gradient Descent Optimization Control of an Activated Sludge Process based on Radial Basis Function Neural Network

摘要

Most systems in science and engineering can bedescribed in the form of ordinary differential equations, but onlya limited number of these equations can be solved analytically.For that reason, numerical methods have been used to get theapproximate solutions of differential equations. Among thesemethods, the most famous is the Euler method. In this paper, anew proposed control strategy utilizing the Euler and thegradient method based on Radial Basis Function Neural Network(RBFNN) model have been used to control the activated sludgeprocess of wastewater treatment. The aim was to maintain theDissolved Oxygen (DO) level in the aerated tank and have thesubstrate concentration Chemical Oxygen Demand (COD 5 )within the standard limits. The simulation results of DO show therobustness of the proposed control method compared to theclassical method. The proposed method can be applied inwastewater treatment systems.