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 : Zhengrui Tao (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Chongyan Cai,Xu Liang,Qinglong An,Zhengrui Tao,Wei-Wei Ming,Ming Chen 한국정밀공학회 2021 International Journal of Precision Engineering and Vol.8 No.2
Cryogenic environments are often adopted in machining difficult-to-cut materials such as Ti-6Al-4V alloy to control its cutting heat and improve machinability. This paper aims to study the machinability of Ti-6Al-4V in finish milling process under four green cutting environments (CEs), i.e. dry, supercritical carbon dioxide (scCO 2 ), supercritical CO 2 -based minimum quantity lubrication with water-based cutting fluid (scCO 2 -WMQL), supercritical CO 2 -based minimum quantity lubrication with oil-on-water droplets cutting fluid (scCO 2 -OoWMQL). Peripheral finish-milling of Ti-6Al-4V was conducted under various cutting speeds, feed rates, radial depth of cut and CEs. The cutting force, cutting temperature, surface morphology and surface roughness were analysed. The experiment results show that the minimum cutting force and its coefficients, cutting temperature and surface roughness are obtained in scCO 2 -OoWMQL environment because of its excellent cooling/ lubrication and chip evacuation performance, whereas the worst friction in the tool-workpiece interface leads to the worst performance under scCO 2 CE. Additionally, the machined surface profile, cutting force and their spectrums under four CEs were studied. The fundamental frequency of machined surface profile is equal to that of cutting force envelope under dry and scCO 2 CEs, which is also called beat frequency, therefore scCO 2 -WMQL and scCO 2 -OoWMQL CEs can improve the milling stability. The results indicate that scCO 2 -OoWMQL provides the best performance with regard to cutting force, cutting temperature, surface finish and clean production.
-
Filter Contribution Recycle: Boosting Model Pruning with Small Norm Filters
Zehong Chen,Zhonghua Xie,Zhen Wang,Tao Xu,Zhengrui Zhang 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.11
Model pruning methods have attracted huge attention owing to the increasing demand of deploying models on low-resource devices recently. Most existing methods use the weight norm of filters to represent their importance, and discard the ones with small value directly to achieve the pruning target, which ignores the contribution of the small norm filters. This is not only results in filter contribution waste, but also gives comparable performance to training with the random initialized weights [1]. In this paper, we point out that the small norm filters can harm the performance of the pruned model greatly, if they are discarded directly. Therefore, we propose a novel filter contribution recycle (FCR) method for structured model pruning to resolve the fore-mentioned problem. FCR collects and reassembles contribution from the small norm filters to obtain a mixed contribution collector, and then assigns the reassembled contribution to other filters with higher probability to be preserved. To achieve the target FLOPs, FCR also adopts a weight decay strategy for the small norm filters. To explore the effectiveness of our approach, extensive experiments are conducted on ImageNet2012 and CIFAR-10 datasets, and superior results are reported when comparing with other methods under the same or even more FLOPs reduction. In addition, our method is flexible to be combined with other different pruning criterions.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
