The Machine Learning Based Finite Element Analysis on Road Engineering of Built-in Carbon Fiber Heating Wire

2018 ◽  
Vol 24 (3) ◽  
pp. 531-541 ◽  
Author(s):  
Yuhua Peng ◽  
Dingyue Chen ◽  
Lihao Chen ◽  
Jiayu Yu ◽  
Mengjie Bao
Keyword(s):  
Machine Learning ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Carbon Fiber ◽  
Element Analysis ◽  
Road Engineering ◽  
Heating Wire

scholarly journals Finite Element Analysis for Nonlinear Unbonded Circular Fiber-Reinforced Elastomeric Bearings

2021 ◽  
Vol 5 (7) ◽  
pp. 170
Author(s):  
Pablo Castillo Ruano ◽  
Alfred Strauss
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Carbon Fiber ◽  
Seismic Isolation ◽  
Nonlinear Viscoelasticity ◽  
Fiber Reinforcement ◽  
Special Focus ◽  
Fiber Reinforced ◽  
Element Analysis ◽  
Elastomeric Bearings

In recent years, interest in low-cost seismic isolation systems has increased. The replacement of the steel reinforcement in conventional elastomeric bearings for a carbon fiber reinforcement is a possible solution and has garnered increasing attention. To investigate the response of fiber-reinforced elastomeric bearings (FREBs) under seismic loads, it is fundamental to understand its mechanical behavior under combined vertical and horizontal loads. An experimental investigation of the components presents complexities due to the high loads and displacements tested. The use of a finite element analysis can save time and resources by avoiding partially expensive experimental campaigns and by extending the number of geometries and topologies to be analyzed. In this work, a numerical model for carbon fiber-reinforced bearings is implemented, calibrated, and validated and a set of virtual experiments is designed to investigate the behavior of the bearings under combined compressive and lateral loading. Special focus is paid to detailed modeling of the constituent materials. The elastomeric matrix is modeled using a phenomenological rheological model based on the hyperelastic formulation developed by Yeoh and nonlinear viscoelasticity. The model aims to account for the hysteretic nonlinear hyper-viscoelastic behavior using a rheological formulation that takes into consideration hyperelasticity and nonlinear viscoelasticity and is calibrated using a series of experiments, including uniaxial tension tests, planar tests, and relaxation tests. Special interest is paid to capturing the energy dissipated in the unbonded fiber-reinforced elastomeric bearing in an accurate manner. The agreement between the numerical results and the experimental data is assessed, and the influence of parameters such as shape factor, aspect ratio, vertical pressure, and fiber reinforcement orientation on stress distribution in the bearings as well as in the mechanical properties is discussed.

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.

The Study on Carbon Fiber Reinforced Concrete Beams Based on Finite Element Analysis

2012 ◽  
Vol 430-432 ◽  
pp. 331-336
Author(s):  
Jian Hua Wang
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Reinforced Concrete ◽  
Carbon Fiber ◽  
Concrete Beams ◽  
Fiber Reinforced Concrete ◽  
Reinforced Concrete Beams ◽  
Fiber Reinforced ◽  
Element Analysis ◽  
Carbon Fiber Reinforced

Carbon fiber-reinforced polymer (CFRP) sheets have recently become popular for use as repair or rehabilitation material for deteriorated carbon fiber reinforced concrete structures. Carbon fiber reinforced concrete beams were analyzed by finite element software ANASYS. Through the finite element analysis, the results showed that using bonded CFRP to strengthen R. C. beams can significantly increase their load carrying capacity. However, the beams with prestressed CFRP can withstand larger ultimate loads than beams with bonded CFRP. Using bonded CFRP to strengthen R. C. beams can obviously reduce the ultimate deflection.

Machine learning predictions on fracture toughness of multiscale bio-nano-composites

2020 ◽  
Vol 39 (15-16) ◽  
pp. 587-598 ◽  
Author(s):  
Vahid Daghigh ◽  
Thomas E Lacy ◽  
Hamid Daghigh ◽  
Grace Gu ◽  
Kourosh T Baghaei ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Machine Learning ◽  
Fracture Toughness ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Nano Composites ◽  
Natural Material ◽  
Element Analysis ◽  
Adaptive Boosting ◽  
Impact Tests

Tailorability is an important advantage of composites. Incorporating new bio-reinforcements into composites can contribute to using agricultural wastes and creating tougher and more reliable materials. Nevertheless, the huge number of possible natural material combinations works against finding optimal composite designs. Here, machine learning was employed to effectively predict fracture toughness properties of multiscale bio-nano-composites. Charpy impact tests were conducted on composites with various combinations of two new bio fillers, pistachio shell powders, and fractal date seed particles, as well as nano-clays and short latania fibers, all which reinforce a poly(propylene)/ethylene–propylene–diene-monomer matrix. The measured energy absorptions obtained were used to calculate strain energy release rates as a fracture toughness parameter using linear elastic fracture mechanics and finite element analysis approaches. Despite the limited number of training data obtained from these impact tests and finite element analysis, the machine learning results were accurate for prediction and optimal design. This study applied the decision tree regressor and adaptive boosting regressor machine learning methods in contrast to the K-nearest neighbor regressor machine learning approach used in our previous study for heat deflection temperature predictions. Scanning electron microscopy, optical microscopy, and transmission electron microscopy were used to study the nano-clay dispersion and impact fracture morphology.

Sign in / Sign up

Export Citation Format

Share Document