Search

Your search keyword '"Wang, Fuming"' showing total 781 results
Start Over Author "Wang, Fuming"
781 results on '"Wang, Fuming"'

5. Influence of Soil Properties on Pile–Soil System Response

Author

Wei, Wei, Wang, Fuming, Yang, Fan, Guo, Chengchao, di Prisco, Marco, Series Editor, Chen, Sheng-Hong, Series Editor, Vayas, Ioannis, Series Editor, Kumar Shukla, Sanjay, Series Editor, Sharma, Anuj, Series Editor, Kumar, Nagesh, Series Editor, Wang, Chien Ming, Series Editor, Cui, Zhen-Dong, Series Editor, Tajima, Yoshimitsu, editor, Aoki, Shin-ichi, editor, and Sato, Shinji, editor

Published
2024
Full Text
View/download PDF

7. Effect of Aging treatment on the Evolution of Precipitates in Super Duplex Stainless Steel

Author

Luo Renzhi, Hu Wenhao, Wang Fuming, Tu Jiangping, Tao Yingqi, Shen Wei

Subjects
duplex stainless steel； precipitates； kinetic； aging treatment, Materials of engineering and construction. Mechanics of materials, TA401-492, Technology
Abstract

The precipitation behavior of precipitates in S32750 super duplex stainless steel was studied by aging treatment at 850 ℃. Thermo-Calc software was used to predict the precipitates and phase composition in tested steel. OM， SEM and EDS were used to analysis the microstructure and precipitates of S32750 super duplex stainless steel after different aging treatment. K-J-M-A model was used to analysis the kinetic of precipitation of σ phase. The results showed that the σ phase was preferred to precipitate at ferrite/austenite boundaries during the aging process at 850 °C. There were two main steps to control the precipitation of σ phase： nucleation control and element diffusion control. In addition， χ phase and Cr2N phase also precipitated during aging treatment. χ was the sub-stable phase， precipitated in the early aging period， and finally transformed into σ phase with the prolongation of aging time.

Published
2024
Full Text
View/download PDF

8. How and what to learn:The modes of machine learning

Author

Feng, Sihan, Zhang, Yong, Wang, Fuming, and Zhao, Hong

Subjects
Computer Science - Machine Learning, Condensed Matter - Disordered Systems and Neural Networks, Physics - Data Analysis, Statistics and Probability, Statistics - Machine Learning
Abstract

Despite their great success, neural networks still remain as black-boxes due to the lack of interpretability. Here we propose a new analyzing method, namely the weight pathway analysis (WPA), to make them transparent. We consider weights in pathways that link neurons longitudinally from input neurons to output neurons, or simply weight pathways, as the basic units for understanding a neural network, and decompose a neural network into a series of subnetworks of such weight pathways. A visualization scheme of the subnetworks is presented that gives longitudinal perspectives of the network like radiographs, making the internal structures of the network visible. Impacts of parameter adjustments or structural changes to the network can be visualized via such radiographs. Characteristic maps are established for subnetworks to characterize the enhancement or suppression of the influence of input samples on each output neuron. Using WPA, we discover that neural network store and utilize information in a holographic way, that is, subnetworks encode all training samples in a coherent structure and thus only by investigating the weight pathways can one explore samples stored in the network. Furthermore, with WPA, we reveal fundamental learning modes of a neural network: the linear learning mode and the nonlinear learning mode. The former extracts linearly separable features while the latter extracts linearly inseparable features. The hidden-layer neurons self-organize into different classes for establishing learning modes and for reaching the training goal. The finding of learning modes provides us the theoretical ground for understanding some of the fundamental problems of machine learning, such as the dynamics of learning process, the role of linear and nonlinear neurons, as well as the role of network width and depth., Comment: 16 pages, 10 figures

Published
2022

10. Effect of ladle-lining materials on inclusion evolution in Al-killed steel during LF refining

Author

Gao Fu-bin, Yan Xinbo, Wang Fuming, Wang Xinhua, and Li Jianli

Subjects
al2o3 lining, al2o3, mgo·al2o3 lining, lf refining, al-killed steel, inclusions, Technology, Chemical technology, TP1-1185, Chemicals: Manufacture, use, etc., TP200-248
Abstract

The effect of lining materials (Al2O3 and Al2O3–MgO·Al2O3) of ladle on evolution of non-metallic inclusions in aluminum-killed (Al-killed) steel during ladle furnace refining without Ca treatment was investigated through industrial experiments. The results showed that non-metallic inclusions experienced the changes from Al2O3 → MgO–Al2O3 → CaO–Al2O3. During the refining process using either of the two ladle lining materials, for all non-metallic inclusions, the vast majority are distributed in the high Al2O3 area of the CaO–Al2O3–MgO phase diagram, with very little or none in the low melting point zone. Non-metallic inclusions are mainly smaller than 3 μm, while those larger than 3 μm consisted primarily of MgO·Al2O3 and CaO–Al2O3 inclusions. The use of an Al2O3–MgO·Al2O3-lining ladle is more effective in reducing the number density of inclusions in the steel. However, during the refining process, the Al2O3-lining ladle does not have a significant impact on the presence of MgO–Al2O3 and CaO–Al2O3 inclusions in the molten steel. The Al2O3–MgO·Al2O3-lining ladle does not have a significant effect on MgO–Al2O3 inclusions, but it does promote the formation of CaO–Al2O3 and CaS inclusions in the molten steel.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results