A Data-Driven Framework for Buckling Analysis of Near-Spherical Composite Shells under External Pressure

2021 ◽  
pp. 1-27
Author(s):  
Mitansh Doshi ◽  
Xin Ning
Keyword(s):  
Machine Learning ◽  
Finite Element ◽  
Learning Model ◽  
External Pressure ◽  
Finite Element Simulations ◽  
Data Driven ◽  
Composite Shells ◽  
Spherical Shells ◽  
Buckling Loads ◽  
Machine Learning Model

Abstract This paper presents a data-driven framework that can accurately predict the buckling loads of composite near-spherical shells (i.e. variants of regular icosahedral shells) under external pressure. This framework utilizes finite element simulations to generate data to train a machine learning regression model based on open-source algorithm Extreme Gradient Boosting (XGBoost). The trained XGBoost machine learning model can then predict buckling loads of new designs with small margin of error without time-consuming finite element simulations. Examples of near-spherical composite shells with various geometries and material layups demonstrate the efficiency and accuracy of the framework. The machine learning model removes the demanding hardware and software requirements on computing buckling loads of near-spherical shells, making it particularly suitable to users without access to those computational resources.

scholarly journals Feature optimization for atomistic machine learning yields a data-driven construction of the periodic table of the elements

2018 ◽  
Vol 20 (47) ◽  
pp. 29661-29668 ◽  
Author(s):  
Michael J. Willatt ◽  
Félix Musil ◽  
Michele Ceriotti
Keyword(s):  
Machine Learning ◽  
Periodic Table ◽  
Chemical Space ◽  
Learning Model ◽  
Data Driven ◽  
Machine Learning Model ◽  
Feature Optimization ◽  
Low Dimensional

By representing elements as points in a low-dimensional chemical space it is possible to improve the performance of a machine-learning model for a chemically-diverse dataset. The resulting coordinates are reminiscent of the main groups of the periodic table.

scholarly journals CarEnvision: A Data-Driven Machine Learning Framework for Automated Car Value Prediction

2021 ◽  
Author(s):  
TianGe (Terence) Chen ◽  
Angel Chang ◽  
Evan Gunnell ◽  
Yu Sun
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Learning Model ◽  
Retail Price ◽  
Data Driven ◽  
Value Prediction ◽  
Learning Framework ◽  
Machine Learning Model ◽  
Negative Sentiment

When people want to buy or sell a personal car, they struggle to know when the timing is best in order to buy their favorite vehicle for the best price or sell for the most profit. We have come up with a program that can predict each car’s future values based on experts’ opinions and reviews. Our program extracts reviews which undergo sentiment analysis to become our data in the form of positive and negative sentiment. The data is then collected and used to train the Machine Learning model, which will in turn predict the car’s retail price.

scholarly journals Numerical Investigations on the Shape Optimization of Stainless-Steel Ring Joint with Machine Learning

2020 ◽  
Vol 11 (1) ◽  
pp. 223
Author(s):  
Minsoo Kim ◽  
Sarang Yi ◽  
Seokmoo Hong
Keyword(s):  
Machine Learning ◽  
Finite Element ◽  
Learning Model ◽  
Training Data ◽  
Metal Ring ◽  
Rubber Ring ◽  
Water Pipes ◽  
Metal Rings ◽  
Machine Learning Model ◽  
Joint Method

Since pipes used for water pipes are thin and difficult to fasten using welding or screws, they are fastened by a crimping joint method using a metal ring and a rubber ring. In the conventional crimping joint method, the metal ring and the rubber ring are arranged side by side. However, if water leaks from the rubber ring, there is a problem that the adjacent metal ring is rapidly corroded. In this study, to delay and minimize the corrosion of connected water pipes, we propose a spaced crimping joint method in which metal rings and rubber rings are separated at appropriate intervals. This not only improves the contact performance between the connected water pipes but also minimizes the load applied to the crimping jig during crimping to prevent damage to the jig. For this, finite element analyses were performed for the crimp tool and process analysis, and the design parameters were set as the curling length at the top of the joint, the distance between the metal rings and rubber rings, and the crimp jig radius. Through FEA of 100 cases, data to be trained in machine learning were acquired. After that, training data were trained on a machine learning model and compared with a regression model to verify the model’s performance. If the number of training data is small, the two methods are similar. However, the greater the number of training data, the higher the accuracy predicted by the machine learning model. Finally, the spaced crimping joint to which the derived optimal shape was applied was manufactured, and the maximum pressure and pressure distribution applied during compression were obtained using a pressure film. This is almost similar to the value obtained by finite element analysis under the same conditions, and through this, the validity of the approach proposed in this study was verified.

Buckling Analyses of Spherical Shells by the Finite Element Method Based on the Willis-Form Equations

2019 ◽  
Vol 11 (09) ◽  
pp. 1950091 ◽  
Author(s):  
Yixiao Sun ◽  
Zhihai Xiang
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
External Pressure ◽  
Experimental Results ◽  
Spherical Shells ◽  
Buckling Loads ◽  
Geometrical Imperfections ◽  
The Impact ◽  
Previous Loading ◽  
Element Method

Buckling analysis of spherical shells under external pressure is a crucial problem in mechanical and aerospace engineering. It is widely known that the buckling loads obtained by classical methods are much higher than experimental results. The main reason for this large discrepancy is customarily attributed to initial geometrical imperfections, and the impact of inhomogeneously distributed stresses during loading process is usually ignored. In order to investigate the effect of this ignored factor, the buckling loads of several spherical shells are analyzed by the geometrically nonlinear finite element method (FEM) based on the Willis-form equations, which explicitly contain the stress gradients at previous loading step. It can be shown that the buckling loads from the Willis-form FEM are about 10% lower than the values from classical FEM. This finding may give better understandings to the differences between theoretical and experimental results for nearly perfect spherical shells and may be helpful to obtain more accurate buckling loads for shells with initial geometrical imperfections.

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

Sign in / Sign up

Export Citation Format

Share Document