Search

To address the problems of low accuracy in fault diagnosis of oil-immersed transformers, poor state perception ability and real-time collaboration during diagnosis feedback, a fault diagnosis method for transformers based on the integration of digital twins is proposed. Firstly, fault sample balance is achieved through Iterative Nearest Neighbor Oversampling (INNOS), Secondly, nine-dimensional ratio features are extracted, and the correlation between dissolved gases in oil and fault types is established. Then, sparse principal component analysis (SPCA) is used for feature fusion and dimensionality reduction. Finally, the Aquila Optimizer (AO) is introduced to optimize the parameters of the Kernel Extreme Learning Machine (KELM), establishing the optimal AO-KELM diagnosis model. The final fault diagnosis accuracy reaches 98.1013%. Combining transformer digital twin models, real-time interaction mapping between physical entities and virtual space is achieved, enabling online diagnosis of transformer faults. Experimental results show that the method proposed in this paper has high diagnostic accuracy and strong stability, providing reference for the intelligent operation and maintenance of transformers. [ABSTRACT FROM AUTHOR]

In this paper, the CO2 (carbon dioxide) exhaled by indoor occupants was used as the tracer gas, and the variation of indoor CO2 concentration in the whole day was observed. Among the 454 samples, 114 and 345 valid samples were screened out which can be used to calculate the daytime and night ventilation rate by the tracer gas method through the sectioning method. The results indicated that seasonal differences in daytime average ventilation are greater than night average ventilation. The highest daytime- average ventilation was found in autumn, next was summer, there was the lowest ventilation in winter. According to the necessary fresh air rate when sleeping at night, night average ventilation rate of 30.1% of samples met the standard. The ventilation rates of different building characteristics were analyzed, residential location, construction age, living floor, room size, window structure, indoor dampness, and window opening habits were all included. The results revealed that the window opening habits was the most significant factor for natural ventilation. Both daytime and night average ventilation rate are basically in the ratio of 2:1 when the windows are opened and closed. moreover, there was higher impact of outdoor climate on daytime average ventilation when window was closed. Significant impact of window structure and indoor dampness on night average ventilation was observed when window was opened. Present study proposed the measurement and determination methods of ventilation when daytime activities of occupants were happened

The thermal environment of large space building with stratified air distribution is characterized by its obvious gradient of vertical temperature, and the stratified air conditioning load (SACL) is closely related to the thermal environment. The Block-Gebhart (B-G) model in summer is established for an actual large space building which has two stratified air distribution (STRAD) systems. One system is the air supply nozzles (ASN) arranged at middle sidewall, the other is the half-cylinder diffusers (HCD) arranged at low sidewall. In order to quickly calculate the air temperature of unoccupied zone (ATUZ), two regression equations for the air temperature gradient under the conditions of two STRAD systems were proposed. Considering six factors, the B-G model was used to calculate 648 cases and the two equations were obtained by multiple regression analysis. Through the field measurement in summer, in three cases of ASN system, the mean absolute error (MAE) between predicted and experimental values of ATUZ was 1.4°C, and the mean absolute percentage error (MAPE) was 4.5%; in three cases of HCD system, the MAE was 1.0°C and the MAPE was 3.0%. The results of this study establish the foundation for the calculation of SACL.