A Quality Monitoring Method of Blast Furnace Hot Metal Based on KPLS Robust Reconstruction Error

Abstract

The invention provides a blast furnace molten iron quality monitoring method based on KPLS robust reconstruction error, which includes: collecting blast furnace operating parameters and molten iron quality variables at the same time; selecting a training set and standardizing it; and mapping the input data in the training set to high-quality variables. dimensional feature space, obtain Gram matrix K and centralize it; obtain new blast furnace operating parameters and hot metal quality variable samples containing abnormal working conditions as test sets and standardize them; map the input data matrix in the test set to high-dimensional feature space Obtain the Gram matrix and centralize it; construct a partial least squares model to describe the high-dimensional feature space and output data matrix; use T 2 Statistics and Q statistics are used to test whether the blast furnace ironmaking process is abnormal; solve the reconstructed values ​​of the original process variable data and identify the process variables that cause the abnormal working conditions of the blast furnace. The invention can accurately identify faults in the quality monitoring of blast furnace molten iron, improve the monitoring performance of molten iron quality, and thereby ensure the quality of blast furnace molten iron.

Description

technical field [0001] The invention belongs to the technical field of blast furnace molten iron quality monitoring, in particular to a blast furnace molten iron quality monitoring method based on KPLS robust reconstruction error. Background technique [0002] Blast furnace ironmaking is an important link in steel production and the main method of modern ironmaking. Due to the good technical and economic indicators of blast furnace ironmaking, simple process, large production volume, high productivity and low energy consumption, the iron produced by this method accounts for more than 95% of the world's total iron. Blast furnace ironmaking is the reduction of iron from iron ore and melting it into pig iron. Blast furnace ironmaking is a continuous production process, and the whole process is completed in the mutual contact process of furnace charge from top to bottom and gas from bottom to top. During the operation of the two major streams of the blast furnace, complex chem...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that fault identification is difficult in the above KPLS-based blast furnace molten iron quality monitoring, the present invention proposes a blast furnace molten iron quality monitoring method based on KPLS robust reconstruction error

Images