scholarly journals Pre-Trained CNN for Classification of Time Series Images of Anti-Necking Control in a Hot Strip Mill

Author(s):  
Samuel Latham ◽  
Cinzia Giannetti
Author(s):  
Qingke Wen ◽  
Zengxiang Zhang ◽  
Shuo Liu ◽  
Xiao Wang ◽  
Chen Wang

1990 ◽  
Vol 87 (1) ◽  
pp. 79-88
Author(s):  
K. Hirata ◽  
Y. Yamamoto ◽  
Y. Ohiké ◽  
J. Sato ◽  
S. Honda ◽  
...  
Keyword(s):  

2001 ◽  
Vol 7 (S2) ◽  
pp. 508-509
Author(s):  
W. Regone ◽  
A. M. 𝚓orge Júnior ◽  
O. Balancin

Upon hot strip mill of titanium Interstitial Free (IF) steels, during cooling from austenite to ferrite region, the level of interstitial elements not removed by steelmaking process is dropped down by Ti that combines with N, C and S. Some authors [1-3] have reported that the traditional precipitation sequence TiN, TiS, Ti4C2S2 and TiC occurs with freestanding particles formed by nucleation and growth processes. Other authors [4] have indicated that the transformation from TiS to Ti4C2S2 may be considered as a hybrid of shear and diffusion, i.e., faulted Ti8S9 (9R) + 10[Ti] + 9[C] → 41/2Ti4C2S2 (or H for its hexagonal crystal structure). At low temperature (≤930°C), the stabilization process continues through epitaxial growth of carbides on H phase. to study the evolution of precipitation upon hot strip mill conditions, samples of a Ti - IF steel were subjected to double straining tests [5] by means of a computerized hot torsion machine, at 1000 °C and 920 °C, with strain rate of 1 s-1 and interpass times ranging from 0.5 to 100 s.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.


Sign in / Sign up

Export Citation Format

Share Document