Banca de QUALIFICAÇÃO: EDUARDO CESAR BEZERRA CAMARA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : EDUARDO CESAR BEZERRA CAMARA
DATE: 24/07/2020
TIME: 09:00
LOCAL: google meet. LINK: https://meet.google.com/bny-zrjt-oyu
TITLE:

Study of the fatigue behavior of power cables with aluminum core using ANNs

KEY WORDS:

Artificial neural networks, aluminum conductor cables, flexion to rigidity, specific weight, constant rigidity, Poffenberger-Swart.

PAGES: 96
BIG AREA: Engenharias
AREA: Engenharia Mecânica
SUBÁREA: Mecânica dos Sólidos
SPECIALTY: Análise de Tensões
SUMMARY:

The continental dimensions of Brazil and the distance from the power generating units (usually hydroelectric) of the consumer centers are factors that raise the importance of the distribution networks, since an unexpected failure due to fatigue in the conducting cables, can reach tens of millions of consumers involving therefore, very high costs. To estimate the remaining cable life of these lines, sophisticated laboratories and long tests are necessary to obtain S-N curves with the same level of average voltage applied in the field. Thus, it becomes desirable a model capable of predicting the resistance to fatigue of conductive cables effectively, simplifying the need for testing and the costs, in addition, of course, the risks of blackout. In this sense, this study seeks to create ANN architectures capable of estimating the fatigue strength of aluminum conducting cables, by varying the cable's structural parameters such as the specific weight (W), the flexural stiffness module (EI) and the Poffenberger-Swart constant K, taking into account the average tension (stretching load) and the number of cycles to which the cables are subjected. The training and testing of the ANNs was done through a set of data obtained from fatigue tests carried out in the cable laboratory of the Fatigue, Fracture and Materials Group (GFFM) of the Federal University of Brasília (UnB) for different types of cables of aluminum alloys. Through the ANNs, constant life diagrams will be constructed for this family of cables, making it possible to compare the results obtained experimentally and those obtained by the ANNs through the mean quadratic error. The results obtained by the ANNs proved to be very promising, managing to generalize the resistance to fatigue for the aluminum conductor cables analyzed.

BANKING MEMBERS:
Presidente - 1338331 - RAIMUNDO CARLOS SILVERIO FREIRE JUNIOR
Interno - 1445637 - WALLACE MOREIRA BESSA
Externo ao Programa - 3138731 - RAPHAEL ARAUJO CARDOSO
Externo à Instituição - BRUNO DA CUNHA DINIZ - UFBA