Yanchao Yin

ABSTRACT The endpoint determination of matte converting directly impacts converter stability, process efficiency, and blister copper quality. To address poor accuracy, high cost, and delayed response in endpoint determination, this paper proposes a non-contact, real-time method using flame images for endpoint prediction in Peirce-Smith converters. Firstly, the flame images are preprocessed through data annotation and augmentation to meet the training requirements of the model.

2. Related Work Many researchers have been working on the challenging issue of removing remote sensing image clouds in recent years, and various technical solutions have been presented. These solutions can basically be divided into three types: multi-spectral-based methods, inpainting-based methods, and multi-temporal-based methods [8], as shown in .

3.1 Descriptive characteristics This study obtained the data from 2016 Q2 to 2021, and a total of 8,379,682 reports were submitted to FAERS. After deduplication and screening, the number of reports with VEN as PS was 19,107. In this study, the PS report data has been analyzed, and the detailed characteristics of the related AEs are shown in Table 1. Among the reported AEs, males (59.96%) accounted for far more than females (34.34%).