Fatigue life prediction of unidirectional glass fiber/epoxy composite laminae using neural networks

Al-Assaf, Yousef; Kadi, H. El

doi:10.1016/s0263-8223(00)00179-3

Cited by 106 publications

(67 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A hybrid learning algorithm is used in order to train the data set. The selection of inputs used in their study was based on the work done by [17]. The interesting part about their study was the investigation on the influence of different membership functions (Triangular-shaped, Gaussian and Bell-shaped) and the number of linguistic values.…”

Section: B Studies Of Degradable Compositesmentioning

confidence: 99%

“…In comparison between membership functions, [16] indicated that the ANFIS model with the Bell-shaped membership function gave a higher accuracy in the prediction of fatigue life. The performance results of the ANFIS model by [16] are compared with the ANN model by [17]. It is found that the ANFIS model with the hybrid neuro-fuzzy method performed better than ANN.…”

Section: B Studies Of Degradable Compositesmentioning

confidence: 99%

See 1 more Smart Citation

Role of Input Selection Prediction of Physical Properties of Degradable Composites Using ANFIS

Bakar¹,

Dom²,

Akbarally³

et al. 2015

IJMMM

View full text Add to dashboard Cite

show abstract

Section: B Studies Of Degradable Compositesmentioning

confidence: 99%

Section: B Studies Of Degradable Compositesmentioning

confidence: 99%

Role of Input Selection Prediction of Physical Properties of Degradable Composites Using ANFIS

Bakar¹,

Dom²,

Akbarally³

et al. 2015

IJMMM

View full text Add to dashboard Cite

show abstract

“…ANN was used to predict the fatigue strength of composites (Aymerich and Serra, 1998;Lee et al, 1998). A Back Propagation Neural Network (BPNN) was used to predict the fatigue failure of a glass fibre/epoxy laminate with a range of fibre orientation angles under various loading conditions (Al-Assaf and EI Kadi, 2001;Mathur et al, 2007). The results obtained were comparable with other prediction methods.…”

Section: Introductionmentioning

confidence: 99%

Estimation of the Dynamic Properties of Epoxy Glass Fabric Composites with Natural Rubber Particle Inclusions

Sankar¹,

Srikant²,

Krishna³

et al. 2013

Int J Automot Mech Eng

View full text Add to dashboard Cite

Conventional materials are being replaced in the field of engineering by composite materials, due to their tailorable properties and high specific properties. These materials are extensively used in structural applications. Damping is one of the important properties of the materials used in structures, and needs to be enhanced in order to reduce structural vibrations. In the present work, the improvement of the material damping of glass fabric epoxy composites with particle rubber inclusions is studied. The effect of particle size on the damping and stiffness parameters at different frequencies and temperatures is studied experimentally. Considerable enhancement in damping without significant reduction in stiffness is observed at lower particle sizes. The damping property in both bending and shear modes is more with 0.254 mm rubber particle inclusions among the selected sizes. A lower reduction in stiffness is observed with the inclusion of lower particle sizes (0.254 mm and 0.09 mm) when compared with higher particle sizes. An ANN-based prediction model is developed to predict these properties for a given frequency/temperature and particle size. The predicted values are very close to the experimental values with an maximum error of 5%.

show abstract

“…Al-Assaf and El Kadi [4] trained a feed-forward neural network (FNN) to predict fatigue failure of unidirectional glass/epoxy under tension-tension and tension-compression loading. They used a unidirectional material with different fiber orientation angles subjected to three stress ratios.…”

Section: Introductionmentioning

confidence: 99%

Predicting the Fatigue Life of Different Composite Materials Using Artificial Neural Networks

2009

View full text Add to dashboard Cite

Artificial Neural Networks (ANN) have been recently used in modeling the mechanical behavior of fiber-reinforced composite materials including fatigue behavior. The use of ANN in predicting fatigue failure in composites would be of great value if one could predict the failure of materials other than those used for training the network. This would allow developers of new materials to estimate in advance the fatigue properties of their material. In this work, experimental fatigue data obtained for certain fiber-reinforced composite materials is used to predict the cyclic behavior of a composite made of a different material. The effect of the neural network architecture and the training function used were also investigated. In general, ANN provided accurate fatigue life prediction for materials not used in training the network when compared to experimentally measured results.

show abstract

Fatigue life prediction of unidirectional glass fiber/epoxy composite laminae using neural networks

Cited by 106 publications

References 9 publications

Role of Input Selection Prediction of Physical Properties of Degradable Composites Using ANFIS

Role of Input Selection Prediction of Physical Properties of Degradable Composites Using ANFIS

Estimation of the Dynamic Properties of Epoxy Glass Fabric Composites with Natural Rubber Particle Inclusions

Predicting the Fatigue Life of Different Composite Materials Using Artificial Neural Networks

Contact Info

Product

Resources

About