RISS 검색 - 국내학술지논문

무료
기관 내 무료
유료

내보내기
내책장담기
한글로보기

정확도순

내림차순

내림차순

10개씩 출력

1
Rotor short‑circuited start‑up strategy for a doubly fed induction machine‑fed large‑rated variable‑speed pumped storage unit operating in pumping mode

Malathy Narayanasamy,Y. Sukhi 전력전자학회 2023 JOURNAL OF POWER ELECTRONICS Vol.23 No.11
The starting time of a large-rated variable-speed pumped storage unit (PSU) operating in pumping mode is crucial in the power balancing scenario in a modern power system because it establishes the transition period from generation to pumping modes, and vice versa, which determines the power system stability. Doubly fed induction machines (DFIM) are preferred in large-rated variable-speed PSUs (> 100 MW) because they ensure variable-speed operation through partial-rated power converters. Initiating the DFIM in pumping mode is challenging, but it is overcome by utilizing rotor-side power converters. The start-up of DFIM is preferred through short-circuiting the stator windings and supplying power to the rotor windings via power converters. However, this task can be performed through either short-circuiting the rotor or stator windings. This work detailed the field-oriented vector control strategies of the rotor short-circuited method and compared the results with the conventional stator short-circuited method in a commercial 306 MVA DFIM-fed variable-speed PSU. Results demonstrate that short-circuiting the rotor windings reduces the starting time and power consumption by 27.5% and 27%, respectively, compared with the typical starting method. This reduced starting time is preferred by the grid authorities because it improves the power system stability. Furthermore, experimental results are validated in the laboratory with a scaled-down unit of 7.5 kW DFIM.
2
State-space model with deep learning for functional dynamics estimation in resting-state fMRI

Suk, H.I.,Wee, C.Y.,Lee, S.W.,Shen, D. ACADEMIC PRESS 2016 NEUROIMAGE Vol.129 No.-
- 원문보기
Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and such functional interaction is not stationary but changes over time. In terms of a large-scale brain network, in this paper, we focus on time-varying patterns of functional networks, i.e., functional dynamics, inherent in rs-fMRI, which is one of the emerging issues along with the network modelling. Specifically, we propose a novel methodological architecture that combines deep learning and state-space modelling, and apply it to rs-fMRI based Mild Cognitive Impairment (MCI) diagnosis. We first devise a Deep Auto-Encoder (DAE) to discover hierarchical non-linear functional relations among regions, by which we transform the regional features into an embedding space, whose bases are complex functional networks. Given the embedded functional features, we then use a Hidden Markov Model (HMM) to estimate dynamic characteristics of functional networks inherent in rs-fMRI via internal states, which are unobservable but can be inferred from observations statistically. By building a generative model with an HMM, we estimate the likelihood of the input features of rs-fMRI as belonging to the corresponding status, i.e., MCI or normal healthy control, based on which we identify the clinical label of a testing subject. In order to validate the effectiveness of the proposed method, we performed experiments on two different datasets and compared with state-of-the-art methods in the literature. We also analyzed the functional networks learned by DAE, estimated the functional connectivities by decoding hidden states in HMM, and investigated the estimated functional connectivities by means of a graph-theoretic approach.

내보내기
내책장담기
한글로보기

정확도순

내림차순

내림차순

10개씩 출력

맨처음 페이지로 1 맨끝 페이지로

상세검색

RISS 보유자료

상세검색

해외전자자료

연관 검색어 추천