Abstract. The control of the dissolved oxygen concentration in an aerobic reactor is one of the most important and challenging tasks, because of its strong nonlinearities and large uncertain dynamics. In this paper a hybrid algorithm is used to approach this nonlinear dynamic system using feedforward neural network to solve the DO concentration control problem. This hybrid algorithm uses different learning algorithm separately. The weights connecting the input and hidden layers are firstly adjusted by a self-organized learning procedure, while the weights between hidden and output layers are trained by supervised learning algorithm, such as a gradient descent method. The simulation examples are provided to demonstrate the efficiency of the approach compared with radial basis function neural network.