Search

Your search keyword '"Wei, Xinchi"' showing total 38 results
Start Over Author "Wei, Xinchi"
38 results on '"Wei, Xinchi"'

6. BSFCDet: Bidirectional Spatial–Semantic Fusion Network Coupled with Channel Attention for Object Detection in Satellite Images.

Author

Wei, Xinchi, Zhang, Yan, and Zheng, Yuhui

Subjects
*OBJECT recognition (Computer vision), *REMOTE sensing, *MILITARY reconnaissance, *URBAN planning, *REMOTE-sensing images, *DEEP learning
Abstract

Due to the increasing maturity of deep learning and remote sensing technology, the performance of object detection in satellite images has significantly improved and plays an important role in military reconnaissance, urban planning, and agricultural monitoring. However, satellite images have challenges such as small objects, multiscale objects, and complex backgrounds. To solve these problems, a lightweight object detection model named BSFCDet is proposed. First, fast spatial pyramid pooling (SPPF-G) is designed for feature fusion to enrich the spatial information of small targets. Second, a three-layer bidirectional feature pyramid network (BiFPN-G) is suggested to integrate the deep feature's semantic information with the shallow feature's spatial information, thus improving the scale adaptability of the model. Third, a novel efficient channel attention (ECAM) is proposed to reduce background interference. Last, a new residual block (Resblock_M) is constructed to balance accuracy and speed. BSFCDet achieves high detection performance while satisfying real-time performance, according to experimental results. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

15. An Improved Analytical Probabilistic Load Flow Method with GMM Models of Correlated DER Generation

Author

Wei Xinchi, Boda Li, Shanshan Shi, Ying Chen, Muchen Yuan, and Guan Huizhe

Subjects
Nonlinear system, symbols.namesake, Computer science, Probabilistic logic, Taylor series, symbols, Applied mathematics, Probability distribution, Quadratic function, Spectral theorem, Mixture model, Cholesky decomposition
Abstract

The increasing penetration of distributed resources (DER) intensifies the volatility in the distribution network. The accurate and efficient method of probabilistic load flow (PLF) becomes a necessity due to the uncertainty and intermittence of DER. Therefore, we propose an improved analytical PLF method to meet the needs of accuracy and efficiency simultaneously. Specifically, the Gaussian mixture model (GMM) is adopted to deal with the uncertainty of the output of DG. Using Taylor expansion, we can obtain the quadratic function to approximate the power flow solution space considering the nonlinearity of the power flow equation. Unlike the previous studies, a set of quadratic functions can be obtained by choosing the mean of each GMM component as the expansion point (EP). Then, the analytical component-based expression of the bus voltage or the branch power flow can be derived according to the spectral theorem and Cholesky decomposition. Eventually, we can acquire the overall probability distribution of the concerned bus voltage by assembling all the component-based distributions. A case study on a 33-bus distribution test system illustrates the efficacy of the proposed method.

Published
2020

38. Modeling and Performance Analysis of a Dual-Stator Brushless Doubly Fed Induction Machine Based on Spiral Vector Theory.

Author

Han, Peng, Cheng, Ming, Wei, Xinchi, and Li, Ning

Subjects
STATORS, INDUCTION machinery, VECTOR analysis, SINGLE-phase flow, ELECTRIC generators, ELECTRIC windings
Abstract

A detailed spiral vector model of the dual-stator brushless doubly fed induction machine is developed, which unifies the steady-state and dynamic analysis into a single-phase basis through introducing complex exponential variables. The modeling method is generalized to well apply to any ac machine with arbitrary winding layout. To validate the effectiveness of the proposed spiral vector model, steady-state characteristics are predicted based on the proposed model and experimentally demonstrated under all possible operation modes, namely, simple induction, cascaded induction, doubly fed synchronous, and double-cascaded induction. The dynamic performance under open-loop operation and closed-loop control is simulated, which is followed by experimental verifications. [ABSTRACT FROM AUTHOR]

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results