Detection method of TFe content of iron ore based on visible-infrared spectroscopy and IPSO-TELM neural network

Abstract

As the main material for industrial production, the TFe content of iron ore determines the grade and quality of iron ore. The existing methods for measuring the TFe content of iron ore either have large errors or take a long time. Therefore, this paper proposes a method for detecting TFe content of iron ore based on IPSO-TELM (two hidden layer extreme learning machine optimized by the improved particle swarm optimization) algorithm using visible-infrared spectroscopy. The IPSO (improved particle swarm optimization) is used to optimize the first hidden layer parameters and the number of the hidden layer nodes in the TELM network. We first obtained iron ore samples from the Anshan mining area. Then, measured the spectral data through the spectral analysis instrument and spectral features are analyzed by PCA (principal component analysis). Finally, we applied the IPSO-TELM algorithm to establish a detection model for TFe. Experiments shows that the IPSO-TELM model has higher detection accuracy and better generalization ability than the TELM and PSO-TELM models. Compared with traditional chemical analysis methods and instrumental analysis methods, this method has great advantages in economy, speed and accuracy.