The utilization of modern automated control systems in copper cathode production offers the opportunity for remote access to control and regulate the electrolytic process parameters. This, in turn, enhances production efficiency while reducing energy costs. The significant parameters in copper electrolytic refining encompass the temperature and composition of the electrolyte, the circulation rate of the electrolyte, the level of sludge, and the frequency of short circuits occurring between the electrodes and the current density. These parameters directly impact the quantity and volume of cathode sludge. The occurrence of short circuits within the bath arises from the growth of dendrites, necessitating the monitoring of voltage, composition, and temperature of the electrolyte. Regular analysis of the electrolyte's composition and the accumulation of sludge volume at the bottom of the electrolyzer is also necessary. The intensification of the electrolysis process primarily involves increasing the current density, reducing the electrode spacing, enhancing the quality of electrodes, improving the electrolyte circulation system, and further mechanizing and automating the process and its auxiliary operations. These efforts contribute to increased productivity. The objective of this study is to expand the capabilities of automated process control systems by incorporating sludge level control sensors. This aims to mitigate irrecoverable losses resulting from dendritic sludge short circuits on the electrodes located in the lower section of the electrolyzer, utilizing new software. A sludge level control method to prevent short circuits has been investigated, and control software employing float-type level sensors has been developed. This measure is projected to decrease energy consumption by 15–20 % and can be effectively implemented in the production of electrolytic copper at the copper smelting plant in Lao Cai, Vietnam.
This paper tackles the challenge of forensic medical image matching (FMIM) using deep neural networks (DNNs). FMIM is a particular case of content-based image retrieval (CBIR). The main challenge in FMIM compared to the general case of CBIR, is that the subject to whom a query image belongs may be affected by aging and progressive degenerative disorders, making it difficult to match data on a subject level. CBIR with DNNs is generally solved by minimizing a ranking loss, such as Triplet loss (TL), computed on image representations extracted by a DNN from the original data. TL, in particular, operates on triplets: anchor, positive (similar to anchor) and negative (dissimilar to anchor). Although TL has been shown to perform well in many CBIR tasks, it still has limitations, which we identify and analyze in this work. In this paper, we introduce (i) the AdaTriplet loss -an extension of TL whose gradients adapt to different difficulty levels of negative samples, and (ii) the AutoMargin method -a technique to adjust hyperparameters of margin-based losses such as TL and our proposed loss dynamically. Our results are evaluated on two large-scale benchmarks for FMIM based on the Osteoarthritis Initiative and Chest X-ray-14 datasets. The codes allowing replication of this study have been made publicly available at https://github.com/Oulu-IMEDS/AdaTriplet.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.