Optimizing models for sustainable drilling operations using genetic algorithm for the optimum ANN

Efkolidis, Nikolaos ; Markopoulos, Angelos ; Karkalos, Nikolaos ; García Hernandez, César (Universidad de Zaragoza) ; Huertas Talon, José Luis (Universidad de Zaragoza) ; Kyratsis, Panagiotis

Resumen: In the present study, Artificial Neural Network (ANN) approaches were adopted for the prediction of thrust force (Fz) and torque (Mz) during drilling of St60 workpiece, according to important cutting parameters such as cutting velocity, feed rate, and cutting tool diameter. During the setup of an ANN, some essential difficulties like the determination of network architecture, the determination of weight coefficients and the selection of training algorithm should be addressed. A combination of genetic algorithm and neural networks (GA-ANN) formulates those difficulties as an optimization problem and resolve it by the help of a suitable optimization method. Finally, a comparison between ANN with network architecture determined by a simple trial and error approach and ANN with architecture determined by a GA-ANN approach is conducted. The comparison of the models showed clearly that adopting genetic algorithm (GA) equals to the improvement of the efficiency of the network performance.

Idioma: Inglés

DOI: 10.1080/08839514.2019.1646014

Año: 2019

Publicado en: APPLIED ARTIFICIAL INTELLIGENCE 33, 10 (2019), 881-901
ISSN: 0883-9514

Factor impacto JCR: 1.172 (2019)

Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 209 / 265 = 0.789 (2019) - Q4 - T3
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 113 / 136 = 0.831 (2019) - Q4 - T3

Factor impacto SCIMAGO: 0.317 - Artificial Intelligence (Q3)

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Expresión Gráfica en Ing. (Dpto. Ingeniería Diseño Fabri.)
Área (Departamento): Área Ing. Procesos Fabricación (Dpto. Ingeniería Diseño Fabri.)