Oil-pumping system control using nonlinear homotopy BP neural network and genetic algorithm

Under loading and empty pumping problems are associated with pumping unit of oil wells and cause waste of energy and inefficient usage of equipment. To solve these problems, a control method combining neural network (NN) and genetic algorithm (GA) is proposed and applied to intermittent oil-pumping control. Especially, the nonlinear homotopy BP NN is proposed to improve the convergence speed of conventional BP NN and overcome its drawback of getting stuck at local minima. The fundamental idea is to identify the pumping model through nonlinear homotopy BP neural network with a nonlinear normalization method, and optimize the downtime through GA. The proposed algorithm is validated with experiments on an actual oil well