In the field of transformer fault diagnosis, the imbalance of fault samples seriously affects the fault identification performance of the diagnosis model. Focusing on the problems of low accuracy and high leakage rate of diagnosis model caused by unbalanced fault samples of transformer, a transformer fault diagnosis method is proposed. First of all, the Borderline SMOTE algorithm is used to balance the fault data set from a few samples on the boundary, so as to achieve the effect of power transformer fault sample equalization. Secondly, a diagnosis model of the stacked sparse auto-Encoders with the gas in oil as input characteristic parameter is built. Finally, an evaluation system consisting of accuracy rate, recall rate and F1 score is selected to compare the diagnosis effect of the model before and after category equalization, the experiment proves the effectiveness of this method.
The molten-salt heat exchanger is a critical heat transfer device used in concentrated solar power systems. In this paper, molten salt heat-transfer performance characteristics and flow resistances in shell and tube heat exchangers with perforated baffles with a notch height of 0.25D (D is the baffle diameter) are simulated. Four opening schemes that use the same opening area (10% of the baffle area) are designed. The numerical results show that the baffle holes can shrink the molten salt flow dead zone significantly and greatly decrease the flow resistance on the shell side at the cost of a slight reduction in the heat-transfer performance. The comprehensive performance of each scheme after opening is higher than that before opening, and the comprehensive performance of Scheme 4 is the best. Next, a genetic algorithm is used to optimize the Scheme 4 opening diameter. The results show that the heat-flux density on the molten-salt side reaches a maximum of 17327 W/m2 when the opening diameter is 2.24 mm. We find that the opening diameter should be maximized to optimize the comprehensive performance at a given pump power. Finally, the data are compared to other correlations. The deviation decreases gradually as the Reynolds number increases. This is because the turbulence enhancement caused by structural change is not substantial at high Reynolds numbers.
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.