A High-precision Finite Element Analysis Using Deep Learning

2018 ◽  
Vol 2018.31 (0) ◽  
pp. 031
Author(s):  
Atsuya OISHI ◽  
Genki YAGAWA
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Deep Learning ◽  
High Precision ◽  
Element Analysis

scholarly journals A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis

2018 ◽  
Vol 15 (138) ◽  
pp. 20170844 ◽  
Author(s):  
Liang Liang ◽  
Minliang Liu ◽  
Caitlin Martin ◽  
Wei Sun
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Deep Learning ◽  
Stress Distribution ◽  
Machine Learning Techniques ◽  
Von Mises Stress ◽  
Patient Specific ◽  
Stress Distributions ◽  
Element Analysis ◽  
Von Mises

Structural finite-element analysis (FEA) has been widely used to study the biomechanics of human tissues and organs, as well as tissue–medical device interactions, and treatment strategies. However, patient-specific FEA models usually require complex procedures to set up and long computing times to obtain final simulation results, preventing prompt feedback to clinicians in time-sensitive clinical applications. In this study, by using machine learning techniques, we developed a deep learning (DL) model to directly estimate the stress distributions of the aorta. The DL model was designed and trained to take the input of FEA and directly output the aortic wall stress distributions, bypassing the FEA calculation process. The trained DL model is capable of predicting the stress distributions with average errors of 0.492% and 0.891% in the Von Mises stress distribution and peak Von Mises stress, respectively. This study marks, to our knowledge, the first study that demonstrates the feasibility and great potential of using the DL technique as a fast and accurate surrogate of FEA for stress analysis.

Finite Element Analysis on Thermal Characteristic of a High Precision Turning Center’s Headstock

2013 ◽  
Vol 313-314 ◽  
pp. 754-758
Author(s):  
Yao Man Zhang ◽  
Ren Jun Gu ◽  
Jia Liang Han
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Temperature Field ◽  
High Precision ◽  
Thermal Characteristic ◽  
Thermal Error ◽  
Analysis Model ◽  
Element Analysis ◽  
Precision Turning ◽  
Turning Center

Theperformances of the turning center will be influenced by its thermalcharacteristics seriously, and accurately predict thermal characteristic of themachine tool is helpful to improve the design level. The headstock of a high precision turning center has been regarded as the researchobjects, and its thermal properties and influence on the performance of the turningcenter are studied. First based the finite element analysis model that has beenconstructed, the steady temperature field distribution and thermal equilibriumtime of the headstock are calculated, and then the temperature field andthermal deformation have been calculated also, and analysis to identify thetrend of the headstock heat distortion are also been done. Some of the keyfactors on the thermal performance of turning center are also studied. Thestudy lays a foundation for the thermal error compensation of the headstock.

Sign in / Sign up

Export Citation Format

Share Document