A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites

D. Lehky, H. Simonova, M. Lipowczan, Z. Kersner (2019). "A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites." In Proceedings of FraMCoS 10, Bayonne, France.

D. Lehky, H. Simonova, M. Lipowczan, Z. Kersner. "A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites." Paper presented at FraMCoS 10, Bayonne, France, 2019.

D. Lehky, H. Simonova, M. Lipowczan, Z. Kersner, "A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites," in Proc. FraMCoS 10, Bayonne, France, 2019.

@inproceedings{d-lehky2019,
  title     = {A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites},
  author    = {D. Lehky, H. Simonova, M. Lipowczan, Z. Kersner},
  year      = {2019},
  booktitle = {Proceedings of FraMCoS 10},
  address   = {Bayonne, France},
}

TY  - CPAPER
TI  - A neural network ensemble for the identification of mechanical fracture parameters of Fine-grained Brittle Matrix Composites
AU  - D. Lehky
AU  - H. Simonova
AU  - M. Lipowczan
AU  - Z. Kersner
PY  - 2019
T2  - Proceedings of FraMCoS 10
CY  - Bayonne, France
UR  - https://framcos.org/wp-content/uploads/framcos-papers/A_neural_network_ensemble_for_the_identification_of_mechanical_fracture_paramete.pdf
AB  - The paper describes a method for the identification of selected mechanical fracture param- eters of fine-grained brittle matrix composites, and its software implementation. The artificial neural network-basedinverseanalysismethodcanbeemployedtoobtainparametersfromexperimentaldata acquired during three-point bending tests on notched prism specimens. This capability is utilized and extended in order to conduct parameter identification on fine-grained brittle matrix composites. Due to the potentially wide range of composite mixtures and hence the wide range of experimental re- sponses of individual specimens, an ensemble of artificial neural networks was created. It allows the entire range of variants to be covered, and provides resulting parameter values with sufficient preci-…
ER  -