Research on Reduction Section Temperature Soft Sensor Model of Hematite-Ore-Beneficiation Shaft Furnace Roasting Process with Compressed Sensing Sampling

• Published in: Sensors & transducers Vol. 157; no. 10; p. 434
• Main Authors: Li, Huayi, Gai, Wenjie
• Format: Journal Article
• Language: English
• Published: Toronto IFSA Publishing, S.L 01.10.2013
• Subjects: Air flow; Beneficiation; Boundary conditions; Chemical reactions; Compressed; Compressed sensing; Gas flow; Hematite; Mathematical models; Measuring instruments; Neural networks; NMR; Nuclear magnetic resonance; PCA; Principal components analysis; Process controls; Product quality; RBF; Reduction; Roasting; Sampling; Sensors; Shaft furnaces; Soft Sensor; Temperature; Transmitters; Variables; Wireless networks
• ISSN: 2306-8515; 1726-5479; 1726-5479

The roasting process of shaft furnace is one of the most important processes in the Minerals Processing Factory. The primary task of it is to provide the roasting ore of hematite with higher magnetism by high temperature deoxidization, in order to fit the request of the integrated production indexes. Traditional math models can't describe the dynamics of many mineral industry processes due to their integrated complexities, and complex association of much technical equipment is in production process. This paper establishes a soft sensor model for predicting the reduction section temperature of shaft furnace roasting, and uses Compressed Sensing (CS) theory for data sampling, combining principal component analysis, case-based reasoning and RBF. The proposed approach can keep the stability of temperature away from some harmful effects, such as big time delay, nonlinearity, etc. With production data of the hematite ore beneficiation process of a plant, the simulation experiments prove that the CS is effective for low rate sampling, and industrial results prove the soft sensor model effectively.