http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Han Jiarui (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Research on Recognition Method of Electrical Components Based on FEYOLOv4-tiny
Gao Jilong,Sun Haoran,Han Jiarui,Sun Qian,Zhong Tie 대한전기학회 2022 Journal of Electrical Engineering & Technology Vol.17 No.6
Recently, electrical component recognition technology is of great signifi cance for fault identifi cation and stable operation of the modern power grids. With the rapid improvement of smart grids, higher requirements are put forward to the recognition methods in detection accuracy and real-time performance. However, the conventional recognition methods are fail to meet the demands since they always have drawbacks in detection performance. To improve the electrical component identifi cation capability, a novel detection method based on Feature Enhanced You Only Look Once v4-tiny (FEYOLOv4-tiny) is proposed in this study. Here, YOLOv4-tiny is employed as the prototype of the proposed network, whereas enhancement module is designed to improve the feature extraction capability. Moreover, frequency channel attention and spatial attention module are utilized to capture the informative and discriminatory features. Experimental results indicate that our proposed method outperforms other lightweight networks in detection accuracy with almost the same real-time performance, especially for the small targets with complex background. Over all, FEYOLO v4-tiny is effi cient in electrical component identifi cation and has signifi cant application prospects in power inspection.
-
Xiangquan Li,Zhengguang Xu,Cheng Han,Jiarui Cui 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.11
The ability to deal with the system disturbance and/or data dropout is often referred to as the robustness of model-free or data-driven control theory. This paper addresses a novel pattern-moving-based partial-form dynamic linearization intermittent model-free adaptive control scheme for a class of nonlinear discrete-time systems with disturbance and random measurement data dropout. Furthermore, the bounded convergence of the tracking error of the closed-loop system is proved by the statistical approach with contraction mapping principle. The basic idea is to consider the pattern-moving-based partial-form dynamic linearization model-free adaptive control method under the condition of missing data which may be caused by network failure, failing sensor or actuator. The designed scheme mainly includes an improved intermittent tracking control law, an intermittent classification-metric bias estimation algorithm and a modified intermittent pseudo gradient vector estimation algorithm. The bounded convergence and effectiveness of the proposed scheme are demonstrated by both the rigorous mathematical inference and two numerical examples.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
