A New Model Based on Improved ACA and BP to Predict Silicon Content in Hot Metal

Abstract

A new model based on improved ant colony algorithm (ACA) and Back-propagation (BP) is proposed to predict Silicon content of hot metal in blast furnace. BP algorithm has been widely used in training artificial neural network (ANN), which is an outstanding model to predict Silicon content. BP algorithm has many attractive features, such as adaptive learning, self- organism, and fault tolerant ability. All of them make BP one of the most successful algorithms in various fields. But BP suffers from relatively slow convergence speed, extensive computations and possible divergence for certain conditions. As a new bionic algorithm, the improved ACA has gained very good performance in solving traveling salesman problem (TSP) and other optimization problems. Its properties such as distributed computation, heuristic searching and robustness have well conquered the long convergence speed and premature problem, which are the main deficiencies of BP algorithm. Experiments show the model proposed has good performance in predicting Silicon content of hot metal.