Temperature Identification of Electrical Heating Furnace Based on Elman Network Combined with Improved PSO
A temperature model of the electrical heating furnace which is commonly used in industry is built by means of Elman neural network combined with an improved particle swarm optimization (IPSO). The input is duty cycle, and IPSO is used to optimize the weights and threshold values of Elman neural network to improve convergence capability and generalization performance of Elman network. Results show that the method performs better than ordinary Elman network in convergence speed and accuracy.
S. Ding et al., "Temperature Identification of Electrical Heating Furnace Based on Elman Network Combined with Improved PSO", Applied Mechanics and Materials, Vols. 20-23, pp. 82-87, 2010