scholarly journals A finite element reduced‐order model based on adaptive mesh refinement and artificial neural networks

2019 ◽  
Vol 121 (4) ◽  
pp. 588-601 ◽  
Author(s):  
Joan Baiges ◽  
Ramon Codina ◽  
Inocencio Castañar ◽  
Ernesto Castillo
Keyword(s):  
Neural Networks ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Adaptive Mesh Refinement ◽  
Mesh Refinement ◽  
Adaptive Mesh ◽  
Reduced Order Model ◽  
Order Model ◽  
Reduced Order ◽  
Artificial Neural

Stress–strain evaluation of structural parts using artificial neural networks

2021 ◽  
pp. 146442072199244
Author(s):  
João PA Ribeiro ◽  
Sérgio MO Tavares ◽  
Marco Parente
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Model Development ◽  
Substantial Reduction ◽  
Reduced Order Model ◽  
Structural Behaviour ◽  
Order Model ◽  
Reduced Order ◽  
Artificial Neural ◽  
Structural Parts

The last decades have been driven by significant progress in the computational capacity, which have been supporting the development of increasingly realistic and detailed simulations. However, despite these improvements, several problems still do not have an effective solution, due to their numerical complexity. As a result, the answer to these problems can be improved by using techniques that enable the description of phenomena with less resolution, but with lower computational costs, which is the case of the reduced order models. The main objective of this article is the presentation of a new approach for reduced order model development and application in the design and optimization of structural parts. The selected method is the artificial neural networks. Artificial neural networks allow the prediction of certain variables based on a given dataset. Two typical case studies are addressed: the first is a fixed plate subjected to uniformly distributed pressure and the second is a reinforced panel also subjected to internal pressure, with regular reinforcements to improve the specific strength. With this method, a substantial reduction in the simulation time is observed, being, approximately, 40 times faster than the solution obtained with Ansys. The developed neural network has a relative average difference of about 20 %, which is considered satisfactory given the complexity of the problem and considering it is a first application of these networks in this domain. In conclusion, this research made it possible to highlight the potential of reduced order model: including the shorter response time, the less computational resources, and the simplification of problems in detriment of less resolution in the description of structural behaviour. Given these advantages, it is expected that these models will play a key role in future applications, as in digital twins.

scholarly journals A Machine Learning Approach as a Surrogate for a Finite Element Analysis: Status of Research and Application to One Dimensional Systems

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1654
Author(s):  
Poojitha Vurtur Badarinath ◽  
Maria Chierichetti ◽  
Fatemeh Davoudi Kakhki
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Stress Distribution ◽  
Maintenance Scheduling ◽  
Element Analysis ◽  
One Dimensional ◽  
Artificial Neural

Current maintenance intervals of mechanical systems are scheduled a priori based on the life of the system, resulting in expensive maintenance scheduling, and often undermining the safety of passengers. Going forward, the actual usage of a vehicle will be used to predict stresses in its structure, and therefore, to define a specific maintenance scheduling. Machine learning (ML) algorithms can be used to map a reduced set of data coming from real-time measurements of a structure into a detailed/high-fidelity finite element analysis (FEA) model of the same system. As a result, the FEA-based ML approach will directly estimate the stress distribution over the entire system during operations, thus improving the ability to define ad-hoc, safe, and efficient maintenance procedures. The paper initially presents a review of the current state-of-the-art of ML methods applied to finite elements. A surrogate finite element approach based on ML algorithms is also proposed to estimate the time-varying response of a one-dimensional beam. Several ML regression models, such as decision trees and artificial neural networks, have been developed, and their performance is compared for direct estimation of the stress distribution over a beam structure. The surrogate finite element models based on ML algorithms are able to estimate the response of the beam accurately, with artificial neural networks providing more accurate results.

Intentional Mistuning With Predominant Aerodynamic Effects

2018 ◽  
Author(s):  
Carlos Martel ◽  
José J. Sánchez
Keyword(s):  
Finite Element ◽  
Traveling Waves ◽  
Element Model ◽  
Simple Expression ◽  
Reduced Order Model ◽  
Action Mechanism ◽  
Aerodynamic Forces ◽  
Order Model ◽  
Reduced Order ◽  
Random Mistuning

Intentional mistuning is a well known procedure to decrease the uncontrolled vibration amplification effects of the inherent random mistuning and to reduce the sensitivity to it. The idea is to introduce an intentional mistuning pattern that is small but much larger that the existing random mistuning. The frequency of adjacent blades is moved apart by the intentional mistuning, reducing the effect of the blade-to-blade coupling and thus the effect of the random mistuning. The situation considered in this work is more complicated because the main source for the blade damping is the effect of the aerodynamic forces (as it happens in a blisk for a family of blade dominated modes with very similar frequencies). In this case the damping is clearly defined for the tuned traveling waves but not for each blade. The problem is analyzed using the Asymptotic Mistuning Model methodology. A reduced order model is derived that allows us to understand the action mechanism of the intentional mistuning, and gives a simple expression for the estimation of its beneficial effect. The results from the reduced model are compared with those from a finite element model of a more realistic rotor under different forcing conditions.

scholarly journals Optimization of a thin-walled element geometry using a system integrating neural networks and finite element method

2017 ◽  
Vol 62 (1) ◽  
pp. 435-442 ◽  
Author(s):  
P. Golewski ◽  
J. Gajewski ◽  
T. Sadowski
Keyword(s):  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Integrated System ◽  
Multilayer Perceptrons ◽  
Optimization Of Geometry ◽  
Thin Walled ◽  
Artificial Neural ◽  
Element Method

Abstract Artificial neural networks [ANNs] are an effective method for predicting and classifying variables. This article presents the application of an integrated system based on artificial neural networks and calculations by the finite element method [FEM] for the optimization of geometry of a thin-walled element of an air structure. To ensure optimal structure, the structure’s geometry was modified by creating side holes and ribs, also with holes. The main criterion of optimization was to reduce the structure’s weight at the lowest possible deformation of the tested object. The numerical tests concerned a fragment of an elevator used in the “Bryza” aircraft. The tests were conducted for networks with radial basis functions [RBF] and multilayer perceptrons [MLP]. The calculations described in the paper are an attempt at testing the FEM - ANN system with respect to design optimization.

Damage quantification in foam core sandwich composites via finite element model updating and artificial neural networks

2020 ◽  
Vol 234 (21) ◽  
pp. 4288-4304
Author(s):  
Ali Mardanshahi ◽  
Masoud Mardanshahi ◽  
Ahmad Izadi
Keyword(s):  
Neural Networks ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Finite Element Model ◽  
Model Updating ◽  
Sandwich Structures ◽  
Element Model ◽  
Foam Core ◽  
Damage Quantification ◽  
Artificial Neural

The main idea of this paper is to propose a nondestructive evaluation (NDE) system for two types of damages, core cracking and skin/core debonding, in fiberglass/foam core sandwich structures based on the inverse eigensensitivity-based finite element model updating using the modal test results, and the artificial neural networks. First, the modal testing was conducted on the fabricated fiberglass/foam core sandwich specimens, in the intact and damaged states, and the natural frequencies were extracted. Finite element modeling and inverse eigensensitivity-based model updating of the intact and damaged sandwich structures were conducted and the parameters of the models were identified. Afterward, the updated finite element models were employed to generate a large dataset of the first five harmonic frequencies of the damaged sandwich structures with different damage sizes and locations. This dataset was adopted to train the machine learning models for detection, localization, and size estimation of the core cracking and skin/core debonding damages. A multilayer perceptron neural network classification model was used for detection of types of damages and also a multilayer perceptron neural network regression model was fitted to the dataset for automatically estimation of the locations and dimensions of damages. This intelligent system of damage quantification was also used to make predictions on real damaged specimens not seen by the system. The results indicated that the extracted natural frequencies from the accurate finite element model, in coordination with the experimental data, and using the artificial neural networks can provide an effective system for nondestructive evaluation of foam core sandwich structures.

Sign in / Sign up

Export Citation Format

Share Document