18 December 2018 in IEEE Journal of Emerging and Selected Topics in Power Electronics
Due to the conductivity of the seawater, the traditional mutual inductance circuit model in the air cannot be used directly to describe wireless power transfer (WPT) systems in seawater applications. This paper proposes a modified mutual inductance circuit model of an underwater WPT system to analyze the eddy current loss (ECL) and the detuning effect caused by the seawater. The time-harmonic electromagnetic field in the seawater and the air near the coil that carries a sinusoidal alternating current is analyzed. The root-mean-square (rms) value and phase angle of the induced voltage on the secondary coil can be obtained by the integral of the electric field intensity along the coil path. By introducing the equivalent ECL impedance at both the primary and secondary sides, a modified mutual inductance circuit model of an underwater WPT system was obtained. Through adding a compensation inductance to the primary circuit, the detuned system in the seawater is turned back to be resonant at the same frequency as in the air. A seawater WPT prototype was built and the experimental results verified the theoretical analysis.
23 June 2023 in Information Processing & Management
23 September 2020 in arXiv
Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Further-more, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge EnhancedRecurrent Network model (KERN) which takes advantage of the capability of deep recurrent neural networks in modeling time-series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed KERN model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.