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 : Chen Xijun (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
TRAFFIC FLOW FORECASTING OF GRAPH CONVOLUTIONAL NETWORK BASED ON SPATIO-TEMPORAL ATTENTION MECHANISM
Zhang Hong,Chen Linlong,Cao Jie,Zhang Xijun,Kan Sunan,Zhao Tianxin 한국자동차공학회 2023 International journal of automotive technology Vol.24 No.4
Accurate traffic flow forecasting is a prerequisite guarantee for the realization of intelligent transportation. Due to the complex time and space features of traffic flow, its forecasting has always been a research hotspot in this field. Aiming at the difficulty of capturing and modelling the temporal and spatial correlation and dynamic features of traffic flow, this paper proposes a novel graph convolutional network traffic flow forecasting model (STAGCN) based on the temporal and spatial attention mechanism. STAGCN model is mainly composed of three modules: Spatio-temporal Attention (STA-Block), Graph Convolutional Network (GCN) and Standard Convolutional Network (CN), model the periodicity, spatial correlation and time dependence of traffic flow respectively. STA-Block module models the spatio-temporal correlation between different time steps through the spatio-temporal attention mechanism and gating fusion mechanism, and uses GCN and CN to capture the spatial and temporal features of traffic flow respectively. Finally, the output of the three components is predicted through a gated fusion mechanism. A large number of experiments have been conducted on two data sets of PeMS. The experimental results demonstrate that compared with the baseline method, the STAGCN model proposed in this paper has better forecasting performance.
-
Investigation of Different Conduction States on the Performance of NMOS-Based Power Clamp ESD Device
Wei Weipeng,Wang Yang,Chen Xijun,Zheng Yifei,Li Jieyu,Cao Pei,Cao Wenmiao 대한전기학회 2021 Journal of Electrical Engineering & Technology Vol.16 No.3
This article investigates the eff ects of diff erent gate coupling voltage and gate voltage duration on electro-static discharge (ESD) performance of several NMOS-based power rail protection devices. Through simulation and transmission line pulse (TLP) test, it is found that there are two modes in the conduction process of the main clamping NMOS: channel conduction state and parasitic NPN conduction state. Diff erent gate voltage and duration bring the two conduction states diff erent proportions in the whole working process, which give the device very diff erent robustness. The results show that under the condition of small gate voltage and long duration and the condition of large gate voltage and short duration, the device can achieve optimal performance because the trigger voltage can be reduced, and the parasitic NPN can be turned on in time to release most of the current
-
Xu Zhou,Wenbiao Jin,Lan Wang,Wanqing Ding,Chuan Chen,Xijun Xu,Renjie Tu,Song-fang Han,Xiaochi Feng,Duu-Jong Lee 한국화학공학회 2020 Korean Journal of Chemical Engineering Vol.37 No.9
Enhancement of sludge dewaterability is key for sludge management and disposal of wastewater treatment plants (WWTP). In this study, the Fe2+-peroxymonosulfate (PMS) conditioning approach was first used to oxidize the primary sludge from the primary sedimentation tank of a full scale WWTP. The combination of Fe2+ (0.05-0.5 g/g TSS) and PMS (0.05-0.5 g/g TSS) could significantly improve the dewaterability of primary sludge. The optimal addition amount of Fe2+ and PMS was 0.1 g/g TSS and 0.25 g/g TSS, respectively, under which the capillary suction time (CST) and specific resistance to filtration (SRF) of the sludge was reduced by 79% and 95%. The physicochemical properties (particle size, zeta potential, EPS composition) of the primary sludge before and after oxidative conditioning were measured. Results showed that sulfate radicals generated from Fe2+-PMS system effectively reduced organic matter in different EPS fractions, further destroying sludge floc cells. Then the bound water in the sludge flocs was released, thereby improving the sludge dewaterability. The microscopic morphology also indicated that the sludge flocs have a blocky structure with tight texture before conditioning. After conditioning, the sludge flocs become smaller, and many irregular pores are formed on the surface, which facilitates the passage of internal moisture. Economic analysis showed that Fe2++PMS conditioning is more economical than the traditional Fenton method.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
