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 : Zhengyi Hu (검색결과 6 건)
- 무료
- 기관 내 무료
- 유료
-
A Multiple Moving Object Segmentation Algorithm Based on Background Modeling and Adaptive Clustering
Zhengyi Hu,Qingchang Tan,Kun Zhang,Xin Wang 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.12
A multiple moving object segmentation algorithm based on Background Modeling and Adaptive Clustering (named as BMAC) algorithm is proposed in this paper. For moving object segmentation, the algorithm uses Chebyshev inequality and the kernel density estimation method to do background modeling firstly. Then in order to classify image pixels as background points, foreground points and suspicious points, an adaptive threshold algorithm is proposed accordingly. After using background modeling, adaptive clustering is used for multi-object segmentation. It defines pixel space connectivity rate and designs a perpendicular split method, initial cluster adaptive splitting and merging self-organizing the iterative clustering segmentation algorithm, without pre-set number of clustering, completes multi-object segmentation for the foreground image. The segmentation results are consistent with the human visual judgment, the use of space connectivity information improve the accuracy of clustering segmentation, comparison and analysis the experimental results show that the proposed algorithm is feasible, rapid and effective.
-
Zhengyi Liu,Juncheng Hu,Qi Sun,Li Chen,Xia Feng,Yiping Zhao 한국고분자학회 2017 Macromolecular Research Vol.25 No.5
In this paper, UV-resistant polypropylene (PP) fibers were prepared with a simple and versatile strategy. The PP fiber was firstly coated a polydopamine (PDA) layer by simply dipping the fiber into an alkaline dopamine solution. Then, the titania (TiO2) nanoparticles were chemically bound to the PDA layer through the reduction capacity of catechol groups in PDA, endowing the fibers with excellent UVresistant properties. The surface chemical composition of modified fibers was confirmed by attenuated total reflectance fourier transform infrared (ATR-FTIR) spectroscopy and X-ray photoelectron spectroscopy (XPS). The surface morphology and the crystalline structure of the modified fibers were studied by scanning electron microscopy (SEM) and X-ray diffraction (XRD) respectively. Thermo stability was characterized by thermogravimetry analysis. Besides, the mechanical and UV protection properties were further investigated through monofilament tensile and the UV transmittance test. The results showed that the PDA and TiO2 were successfully coated on fiber surface. Comprared to the pristine fiber, the modified fiber exhibited better thermal stability. Particularly, the as-prepared PP-PDA-TiO2 fibers could strongly resist the UV rays with no change in mechanical properties.
-
Few-shot transfer learning with attention for intelligent fault diagnosis of bearing
Yao Hu,Qingyu Xiong,Qiwu Zhu,Zhengyi Yang,Zhiyuan Zhang,Dan Wu,Zihui Wu 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.12
The bearing is one of the key components in modern industrial equipment. In the past few years, many studies have been carried out on bearing diagnosis through datadriven methods. However, there are two practical problems. First, under actual working conditions, the lack of fault samples is a major factor that hinders the application of these methods in industrial environments. Second, there is a lack of full utilization of a priori knowledge in the current stage of methods using relational networks for fault diagnosis. It is manifested by the incompleteness of the relational network structure. To address these problems, we present a new diagnosis method based on few-shot learning, which is suitable for the environment where the data is scarce. In this method, we train the model with the data generated by the artificial damaged bearings instead of the data from the real bearing. We experimentally validate the performance improvement of the complete relational network structure. It is able to perform the few-shot learning task better. In addition, we also reduce the global feature discrepancy by introducing an attention mechanism to improve the performance of the model. And the impact of the number of layers of the attention mechanism on the model is also discussed in detail. In this paper, our model performs better under the same experimental conditions compared with other transfer learning models.
-
-
Junyu Tian,Guang Xu,Zhengyi Jiang,Haijiang Hu,Mingxing Zhou 대한금속·재료학회 2018 METALS AND MATERIALS International Vol.24 No.6
The effects of Nickle (Ni) addition on bainitic transformation and property of ultrahigh strength bainitic steels are investigatedby three austempering processes. The results indicate that Ni addition hinders the isothermal bainite transformation kinetics,and decreases the volume fraction of bainite due to the decrease of chemical driving force for nucleation and growth ofbainite transformation. Moreover, the product of tensile strength and total elongation (PSE) of high carbon bainitic steelsdecreases with Ni addition at higher austempering temperatures (220 and 250 °C), while it shows no significant differenceat lower austempering temperature (200 °C). For the same steel (Ni-free or Ni-added steel), the amounts of bainite and RAfirstly increase and then decrease with the increase of the austempering temperature, resulting in the highest PSE in thesample austempered at temperature of 220 °C. In addition, the effects of austempering time on bainite amount and propertyof high carbon bainitic steels are also analyzed. It indicates that in a given transformation time range of 30 h, more volumeof bainite and better mechanical property in high carbon bainitic steels can be obtained by increasing the isothermal transformationtime.
-
In‑Situ Observation of Martensitic Transformation in a Fe–C–Mn–Si Bainitic Steel During Austempering
Junyu Tian,Guang Xu,Zhengyi Jiang,Haijiang Hu,Qing Yuan,Xiangliang Wan 대한금속·재료학회 2020 METALS AND MATERIALS International Vol.26 No.7
The martensitic transformation in a Fe–C–Mn–Si bainitic steel was examined by in situ high-temperature laser scanningconfocal microscopy (LSCM) and dilatometry. The phenomenon of continuous martensitic transformation during austemperingwas firstly dynamically observed by LSCM. Differing from the commonly accepted viewpoint on martensite formationin bainitic steels, the martensitic transformation in the conventional medium-carbon bainitic steel was not instantaneous andproceeded gradually when the sample was austempered below martensite starting temperature (MS). It can be attributed tothe generation of internal stresses, thermal activation, stimulating nucleation, and the segregation of Mn. In addition, apartfrom the continuous martensitic transformation, the bainitic transformation was also directly observed by LSCM duringaustempering below MS. Moreover, it was clear from the results of dilatation during austempering that the inflection point inthe dilatation curve against time was not the demarcation point between martensitic and bainitic transformation, and in situobservations confirmed that martensite was still formed after the inflection point. Therefore, the obtained results could be anexcellent reference to further understand the mechanism of bainitic and martensitic transformations in Fe–C–Mn–Si bainiticsteel during austempering below MS.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
