http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A new fault diagnosis method based on convolutional neural network and compressive sensing
Yunfei Ma,Xisheng Jia,Huajun Bai,Guozeng Liu,Guanglong Wang,Chiming Guo,Shuangchuan Wang 대한기계학회 2019 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.33 No.11
Compressive sensing is an efficient machinery monitoring framework, which just needs to sample and store a small amount of observed signal. However, traditional reconstruction and fault detection methods cost great time and the accuracy is not satisfied. For this problem, a 1D convolutional neural network (CNN) is adopted here for fault diagnosis using the compressed signal. CNN replaces the reconstruction and fault detection processes and greatly improves the performance. Since the main information has been reserved in the compressed signal, the CNN is able to extract features from it automatically. The experiments on compressed gearbox signal demonstrated that CNN not only achieves better accuracy but also costs less time. The influencing factors of CNN have been discussed, and we compared the CNN with other classifiers. Moreover, the CNN model was also tested on bearing dataset from Case Western Reserve University. The proposed model achieves more than 90 % accuracy even for 50 % compressed signal.
Yunfei Dai,Wei Ma,Tong Zhang,Jinwei Yang,Chenghao Zang,Kuangpin Liu,Xianbin Wang,Jiawei Wang,Zhen Wu,Xingkui Zhang,Chunyan Li,Junjun Li,Xiangpeng Wang,Jianhui Guo,Liyan Li 한국생물공학회 2020 Biotechnology and Bioprocess Engineering Vol.25 No.3
Long noncoding RNAs (lncRNAs) play important roles in the process of cell fate determination. However, their function and expression profiles have not yet been systematically investigated during the transdifferentiation of glial precursor cells derived from dorsal root ganglia (DRG) in the peripheral nervous system. Our results demonstrated significant differences in gene architecture and expression among the three transcript types (lncRNA, mRNA, and TUCP). Distinct differences in transcript length, exon number, and ORF length were identified between lncRNAs and mRNAs after comparative analysis of their structure and sequence conservation. We found that the upregulated lncRNAs outnumbered the downregulated lncRNAs in glial precursor cells cultured with proBDNF antiserum compared with the levels in glial precursor cells cultured without proBDNF antiserum. By a series of GO and KEGG analyses, we found that the effects of some lncRNAs on their target genes in cis were related to nerve growth factor-induced cell cycle, cell phenotype change, and neuronal differentiation. The qRT-PCR verification results of lncRNAs ENSRNOT00000091991, ENSRNOT00000087717, and LNC_000429 were mostly consistent with the sequencing results. The candidate lncRNAs may be associated with the neuronal transdifferentiation of glial precursor cells. Our study provides the first evidence for a remarkably diverse pattern of lncRNA expression during neuronal differentiation of glial precursor cells from rat DRG, and also provides a resource for lncRNA studies in the field of cell differentiation.
Effects of Reynolds number on the flow field in a low-pressure turbine with incoming wakes
Xu Zhao,Yunfei Wang,Xiaozhong Ma,Yaowen Zhang,Long Yue,Bin Zheng 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.11
In order to further understand the effects of the Reynolds number on the flow field within a low-pressure turbine with incoming wakes, the transition SST turbulence model was employed for numerical simulation under four Reynolds number conditions ranging from 0.6×10 5 to 3.0×10 5 . The numerical results showed that the boundary layer separation at the rear part of the suction surface was prone to occur in the condition of low Reynolds number (Re 2th = 0.6×10 5 ), and the separation bubble was semi-open and semi-closed. The separation bubble impedes the development of the passage vortex and wall vortex towards mid-span region. When the Reynolds number exceeds 1.0×10 5 , boundary layer separation does not occur. The influence of Reynolds number on the total pressure loss coefficient is primarily evident on the suction surface side, and the growth rate of total pressure loss coefficient first increases and then decreases along the streamwise direction. As the Reynolds number increases from 0.6×10 5 to 3.0×10 5 , the peak point location of total pressure loss decreases by approximately 12 %. The influence of Reynolds number on corner vortex and wall vortex is relatively more sensitive compared to that of passage vortex.
汤云飞 ( Tang-yunfei ),马宜菲 ( Ma-yifei ) 경상대학교 교육연구원 2022 중등교육연구 Vol.34 No.2
20世纪90年代伊始, 计算机、计算机网络技术等现代数码信息技术快速发展并且应用范围越来越广。在互联网的快速发展与外来文化大量流入中国市场的背景下, 中国青少年心理年龄成熟时间大大提前。由于数码网络天然的隐蔽性与复杂性, 出现越来越多基于数码网络的新兴犯罪形式。并且由于中国社会结构与家庭结构的快速变化, 破碎和单亲家庭增多, 且目前无论家庭还是学校社会都缺乏系统完整性教育。在各种因素的综合影响下, 青少年数码性犯罪问题日益严重, 成为影响青少年正常成长及危害社会治安的一个严重的社会问题, 如何预防青少年数码性犯罪就显得越发重要。本文就青少年数码性犯罪的概念特点以及原因进行了分析, 并结合中国现行法律制度, 提出中国在青少年数码性犯罪预防教育中存在的问题并提出相应的解决对策, 以期对解决这一严重的现实问题有所帮助。 At the beginning of the 1990s, modern digital information technology such as computer and computer network technology developed rapidly and its application became more and more extensive. Under the background of the rapid development of the Internet and the influx of foreign culture into our market, the psychological maturity of our teenagers is advanced greatly. Due to the natural concealment and complexity of digital network, more and more new forms of crime based on digital network appear. And because of the rapid change of social structure and family structure, the number of broken and single-parent families is increasing. Under the comprehensive influence of various factors, the problem of juvenile digital sex crimes is becoming more and more serious, which affects the normal growth of Chinese teenagers and endangers the public order. This paper analyzes the conceptual characteristics and causes of juvenile digital sex crimes, and puts forward the problems and corresponding countermeasures in China's digital sex crime prevention education.