18 August 2023 in IEEE Transactions on Industrial Informatics
Nonintrusive load monitoring (NILM) identifies the status and power consumption of various household appliances by disaggregating the total power usage signal of an entire house. Efficient and accurate load monitoring facilitates user profile establishment, intelligent household energy management, and peak load shifting. This is beneficial for both the end users and utilities by improving the overall efficiency of a power distribution network. Existing approaches mainly focus on developing an individual model for each appliance. Those approaches typically rely on a large amount of household-labeled data that are hard to collect. In this article, we propose a multi-appliance-task framework with a training-efficient sample augmentation (SA) scheme that boosts the disaggregation performance with limited labeled data. For each appliance, we develop a shared-hierarchical split structure for its regression and classification tasks. In addition, we also propose a 2-D attention mechanism in order to capture spatio-temporal correlations among all appliances. With only one-day training data and limited appliance operation profiles, the proposed SA algorithm can achieve comparable test performance to the case of training with the full dataset. Finally, simulation results show that our proposed approach features a significantly improved performance over many baseline models. The relative errors can be reduced by more than 50% on average.
28 March 2023 in Advances in Engineering Technology Research
In the rapid development of social economy, people's quality of life is getting higher and higher, elevator as one of the essential means of transportation in daily life, how to ensure the safety and stability of elevator equipment operation, has become the main issue of research and discussion. Since the sensors in the elevator can collect a large amount of data information, which can provide effective basis for the study of the operating state of the elevator equipment, scientific researchers propose to use big data technology to optimize the elevator safety detection and management, build a sound management system and monitoring methods, and solve the elevator safety failures and abnormal situations as soon as possible. In this paper, on the basis of understanding the research status of elevator safety detection management, according to the theory of big data technology, put forward the elevator safety detection management system with big data as the core, and combined with practical cases for verification and analysis. The final results show that the application of big data technology in elevator safety detection management is very important.