Finding substitutes for sulfur hexafluoride (SF6), a gas with extremely high global warming potential, has been a persistent effort for years in the field of high voltage power equipment, which focuses on the evaluation of the electrical strength and boiling temperature for the practical purpose. Following up the previous proposed linear regression models, this work introduces machine learning algorithms including artificial neural network (ANN) and random forest (RF) as the potential approaches to predict the electrical strength and boiling temperature. Based on a series of descriptors derived from the molecular structure of 74 molecules, the performance of three different methods: multiple linear regression, artificial neural network and random forest are compared and assessed in terms of the sensitivity to the sample size, prediction accuracy and stability, and the interpretability of predictors. Considering the available data are limited, random forest shows superior performance with higher robustness and efficiency. The same approaches were applied to the boiling temperature and random forest produced better results as well. Besides, the variable importance ranked by RF improves understanding of the correlation between the molecular properties and electrical strength. It provides important insights to analyze the properties of the SF6 substitutes during the design and synthesis of the new eco-friendly gases in power equipment.
In this paper, the radial temperature distributions of the blown CO 2 arcs in a model gas circuit breaker were investigated by optical emission spectroscopy methods. The CO 2 flows with different flow rates (50, 100 and 150 l min −1 ) were created to axially blow the arcs burning in a polymethyl methacrylate (PMMA) nozzle. Discharges with different arc currents (200 and 400 A) were conducted in the experiment. The absolute intensity method was applied for a carbon ionic line of 657.8 nm to obtain the radial temperature profiles of the arc columns at a cross-section 1 mm above the nozzle. The calibration for the intensity of the C II 657.8 nm line was achieved by the Fowler-Milne method with the help of an oxygen atomic line of 777.2 nm. The highest temperature obtained in the arc center was up to 19 900 K when the arc current was 400 A and the CO 2 flow rate was 50 l min −1 , while the lowest temperature in the arc center was about 15 900 K when the arc current was 200 A and the CO 2 flow rate was 150 l min −1 . The results indicate that as the arc current increases, the temperature in the arc center would also increase apparently, and a larger gas flow rate would lead to a lower central temperature in general. It can also be found that the influence of the CO 2 flow rate on the arc temperature was much less than that of the arc current under the present experimental conditions. In addition, higher temperature in the arc center would cause a sharper temperature decrease from the central region towards the edge.
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.