A Blast Furnace Burden Surface Deeplearning Detection System Based on Radar Spectrum Restructured by Entropy Weight

Abstract

Accurately capturing the burden surface information of a blast furnace (BF) is helpful to adjust the burden distribution matrix and improve the gas flow distribution, which is essential in the steel smelting industry. However, it is difficult to detect the burden surface because of the high temperature, high pressure, high dust and flame combustion environment condition inside the BF, in addition to the fluidization characteristics of the burden surface. With the fusion of high-temperature metallurgy, radar detection and image processing, a new BF surface deep-learning detection system based on energy weight was developed in this study to visualize the smelting status of a BF and digitize the information of the burden surface. First, the original burden surface echo spectrogram was captured using a frequency-modulated continuous wave radar with a high-temperature-resistant sensor. Second, the point cloud distribution map was constructed based on the principle of synthetic aperture radar (SAR) imaging. The coordinate transformation and matrix compensation were completed by the entropy weight method and Gamma correction to convert point cloud map to the burden surface grayscale image, constructing datasets for the network. Third, with a 3rd-order hourglass feature extraction network, a BF surface detection network based on the principle of YOLOv3 was designed and trained to predict the position of the burden surface in the grayscale image and track the changing trend of the burden line. The proposed method, which is tested on two steel plant datasets, achieved an average prediction precision of 99.74%. Finally, compared with the traditional burden line extraction algorithm, burden line oscillations and local outliers can be avoided by the proposed method. The continuous detection of the BF surface information was realized.