An improved ELM algorithm for the measurement of hot metal temperature in blast furnace

This note proposes a modified ELM algorithm named P-ELM subject to how to get rid of the multicollinear problem in calculation based on PCA technique. By reducing the dimension of hidden layer output matrix (H  ) without loss major information through PCA theory, the proposed P-ELM algorithm can not only ensure the full column rank of newly generated hidden layer output matrix (H′H′), but also improve the training speed. In order to verify the effectiveness of P-ELM algorithm, this paper establishes a soft measurement model for hot metal temperature in the blast furnace (BF). Some comparative simulation results with other famous feedforward neural network and the ordinary ELM algorithm with its variants illustrate the better generalization performance and stability of the proposed P-ELM algorithm.