Multi-stage regression linear parametric models of room temperature in office buildings

2012 ◽  
Vol 56 ◽  
pp. 69-77 ◽  
Author(s):  
Siyu Wu ◽  
Jian-Qiao Sun
Keyword(s):  
Room Temperature ◽  
Parametric Models ◽  
Office Buildings ◽  
Multi Stage

Finite Element Prediction of Temperature Variation of Material and Dies in Aluminum Forging

2020 ◽  
Vol 830 ◽  
pp. 93-100
Author(s):  
Jae Dong Yoo ◽  
Tae Min Hwang ◽  
Man Soo Joun
Keyword(s):  
Aluminum Alloy ◽  
Temperature Rise ◽  
High Speed ◽  
Room Temperature ◽  
High Strain ◽  
Cold Forging ◽  
Multi Stage ◽  
Aluminum Forging ◽  
The Right ◽  
Finite Element Prediction

Investigation into behaviors of aluminum alloy to be metal formed at the room temperature is conducted in this study. An index is used to evaluate the sensitivity of temperature, that is, index of relative normalized temperature rise to steel called normalized temperature rise index per steel which helps researchers to obtain some insight on new materials based on experiences of steel forging. An investigation to an aluminum alloy shows that the index is quite high, implying that temperature effect as well as rate-dependence effect on the forming processes of aluminum alloy at the room temperature cannot be neglected. Some details of thermomechanical predictions of a relatively high-speed automatic multi-stage forging process of a yoke with highly deformed region are given to reveal the importance of temperature and/or strain rate even in cold forging of aluminum alloy parts with high speed and high strain. All manuscripts must be in English, also the table and figure texts, otherwise we cannot publish your paper. Please keep a second copy of your manuscript in your office. When receiving the paper, we assume that the corresponding authors grant us the copyright to use the paper for the book or journal in question. Should authors use tables or figures from other Publications, they must ask the corresponding publishers to grant them the right to publish this material in their paper. Use italic for emphasizing a word or phrase. Do not use boldface typing or capital letters except for section headings (cf. remarks on section headings, below).

scholarly journals Automatic Multi-Stage Cold Forging of an SUS304 Ball-Stud with a Hexagonal Hole at One End

Materials ◽  
2020 ◽  
Vol 13 (22) ◽  
pp. 5300
Author(s):  
Jong Bok Byun ◽  
Mohd Kaswandee Razali ◽  
Chang Ju Lee ◽  
Il Dong Seo ◽  
Wan Jin Chung ◽  
...  
Keyword(s):  
Flow Stress ◽  
Room Temperature ◽  
Cold Forging ◽  
Material Strength ◽  
Element Analysis ◽  
Multi Stage ◽  
Plastic Deformation Behavior ◽  
Die Stress ◽  
Hexagonal Hole ◽  
Good Strain

SUS304 stainless steel is characterized by combined tensile and compression testing, with an emphasis on flow stress at higher strain and temperature. The plastic deformation behavior of SUS304 from room temperature to 400 °C is examined and a general approach is used to express flow stress as a closed-form function of strain, strain rate, and temperature; this is optimal when the strain is high, especially during automatic multi-stage cold forging. The fitted flow stress is subjected to elastothermoviscoplastic finite element analysis (FEA) of an automatic multi-stage cold forging process for an SUS304 ball-stud. The importance of the thermal effect during cold forging, in terms of high material strength and good strain-hardening, is revealed by comparing the forming load, die wear and die stress predictions of non-isothermal and isothermal FEAs. The experiments have shown that the predictions of isothermal FEA are not feasible because of the high predicted effective stress on the weakest part of the die.

Hybrid Architecture based on RNN-SVM for Multilingual Handwriting Recognition using Beta-elliptic and CNN models

2021 ◽  
Author(s):  
Yahia Hamdi ◽  
Houcine Boubaker ◽  
Besma Rabhi ◽  
Wael Ouarda ◽  
Adel Alimi
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Handwriting Recognition ◽  
Parametric Models ◽  
Learning Approaches ◽  
Discrimination Power ◽  
Feature Vectors ◽  
Multi Stage ◽  
Online Handwriting Recognition ◽  
Online Handwriting

Currently, deep learning approaches have proven successful in the areas of handwriting recognition. Despite this, research in this field is still needed, especially in the context of multilingual online handwriting recognition scripts by adopting new network architectures and combining relevant parametric models. In this paper, we propose a multi-stage deep learning-based algorithm for multilingual online handwriting recognition based on hybrid deep Bidirectional Long Short Term Memory (DBLSTM) and SVM networks. The main contributions of our work lie in partly in the composition of a new multi-stage architecture of deep learning networks associated with effective feature vectors that integrate dynamic and visual characteristics. First, the proposed system proceeds by pretreating the acquired script and delimiting its Segments of Online Handwriting Trajectories (SOHTs). Second, two types of feature vectors combining BetaElliptic Model (BEM) and Convolutional Neural Network (CNN) are extracted for each SOHT in order to fuzzy classify them into k sub-groups using DBLSTM neural networks for both online and offline branches trained using an unsupervised fuzzy k-means algorithm. Finally, we combine the trained models to strengthen the discrimination power of the global system using SVM engine. Extensive experiments on three data sets were conducted to validate the performance of the proposed method. The experimental results show the effectiveness and complementarities of the individual modules and the advantage of their fusion.<br>

scholarly journals Hybrid Architecture based on RNN-SVM for Multilingual Online Handwriting Recognition using Beta-elliptic and CNN models

2021 ◽  
Author(s):  
Yahia Hamdi ◽  
Houcine Boubaker ◽  
Besma Rabhi ◽  
Wael Ouarda ◽  
Adel Alimi
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Handwriting Recognition ◽  
Parametric Models ◽  
Learning Approaches ◽  
Discrimination Power ◽  
Feature Vectors ◽  
Multi Stage ◽  
Online Handwriting Recognition ◽  
Online Handwriting

Currently, deep learning approaches have proven successful in the areas of handwriting recognition. Despite this, research in this field is still needed, especially in the context of multilingual online handwriting recognition scripts by adopting new network architectures and combining relevant parametric models. In this paper, we propose a multi-stage deep learning-based algorithm for multilingual online handwriting recognition based on hybrid deep Bidirectional Long Short Term Memory (DBLSTM) and SVM networks. The main contributions of our work lie in partly in the composition of a new multi-stage architecture of deep learning networks associated with effective feature vectors that integrate dynamic and visual characteristics. First, the proposed system proceeds by pretreating the acquired script and delimiting its Segments of Online Handwriting Trajectories (SOHTs). Second, two types of feature vectors combining BetaElliptic Model (BEM) and Convolutional Neural Network (CNN) are extracted for each SOHT in order to fuzzy classify them into k sub-groups using DBLSTM neural networks for both online and offline branches trained using an unsupervised fuzzy k-means algorithm. Finally, we combine the trained models to strengthen the discrimination power of the global system using SVM engine. Extensive experiments on three data sets were conducted to validate the performance of the proposed method. The experimental results show the effectiveness and complementarities of the individual modules and the advantage of their fusion.<br>

Room Temperature Lasing of Multi-Stage Quantum-Cascade Lasers at 8 μm Wavelength

2018 ◽  
Vol 52 (8) ◽  
pp. 1082-1085 ◽  
Author(s):  
A. V. Babichev ◽  
A. G. Gladyshev ◽  
A. S. Kurochkin ◽  
E. S. Kolodeznyi ◽  
G. S. Sokolovskii ◽  
...  
Keyword(s):  
Room Temperature ◽  
Quantum Cascade Lasers ◽  
Quantum Cascade ◽  
Multi Stage ◽  
Cascade Lasers

Modelling the Combined Effect of Room Temperature Storage and Cold Deformation on the Age-Hardening Behaviour of Al-Mg-Si Alloys-Part 1

2014 ◽  
Vol 794-796 ◽  
pp. 670-675 ◽  
Author(s):  
Ole Runar Myhr ◽  
Carmen Schafer ◽  
Øystein Grong ◽  
Olaf Engler ◽  
Henk Jan Brinkman ◽  
...  
Keyword(s):  
Room Temperature ◽  
Cold Deformation ◽  
Theoretical Background ◽  
Age Hardening ◽  
Room Temperature Storage ◽  
Hardening Model ◽  
Industrial Processing ◽  
Automotive Body ◽  
Multi Stage ◽  
Temperature Storage

In the present paper, an extended age hardening model for Al-Mg-Si alloys is presented. In this new approach the combined precipitation, yield strength and work hardening model, known as NaMo Version 1, has been further developed to account for the effects of room temperature storage and cold deformation on the resulting age hardening behaviour. Incorporation of these two new stages in NaMo largely increases the versatility of the model by allowing simulations of complex multi-stage industrial processing involving thermomechanical treatment as well. Part 1 of this work deals with the theoretical background and experimental validation of the extended version of NaMo, while Part 2 focuses on the new applications of the model by showing some numerical examples related to production of automotive body panels.

Sign in / Sign up

Export Citation Format

Share Document