Abstract
Short circuit is a key factor which drastically affects the efficiency of metal electrorefining. Infrared image of the intercell busbar region is used to perform short circuit detection. To cope with the high thermal background, a two-level short circuit detection method is designed. Firstly, with background subtraction, high intensity short circuit electrodes, as well as the background, are removed, and normal working electrodes are preserved. In the second stage, suspicious short circuit areas are sifted out by normal electrode detecting and texture period estimation. Gaussian difference filter (DoG) which is based on the human visual system is improved to match the target gray distribution. A comparative experiment indicates that the proposed orthogonal DoG outperforms the original DoG and top-hat in the accuracy of normal electrode detection. The two-level detection method in this paper is applied in a copper electrolysis plant and exhibits superiority in locating short circuits and avoiding miss detection.
Highlights
Base on the period of the texture, the circle areas in Figure 14 are selected as suspicious short circuit areas that belong to the target cell. ere are nine suspicious short circuit areas obtained with the improved orthogonal difference of Gaussian filter (DoG) method, while the number of that with the DoG filter is eleven
The four known short circuits are all included in the suspicious short circuit areas determined by the two methods, it is obvious that the lateral distances of the suspicious short circuit areas obtained by the orthogonal DoG method are smaller
E system detected 76 apparent high temperature short circuits, 13 of which were fault-detected, and these misdetected electrodes were short circuited electrodes that had been excluded, their temperature had not returned to normal. 99 potential short circuits were diagnosed, of which 87 were detected by error. e main reason for the high error detection is that the uneven current distribution leads to an increase in the number of blurry areas on the busbar, which are diagnosed as suspicious short circuit areas
Summary
The intercell busbar area is proposed as the RoI in this paper based on the temperature characteristics of the area. The high thermal background and the compact electrode distribution pose challenges for high temperature short circuit target detection. Note that normal working suspenders on the busbar keep better contrast with the background. Combining this characteristic with the regular texture of the busbar area, we design a two-level detection scheme (Figure 3). The background subtraction highlights these preserved normal working suspenders, these small and dim targets are still hidden in a heavy clutter due to the complex grayscale distribution of the intercell busbar area, which bring obstacles for detection.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
