Estimación del consumo específico de energía en el torneado de alta velocidad del acero AISI-1045 utilizando redes neuronales // Assessment of the specific energy consumption in high speed turning of AISI-1045 steel using neural networks
Abstract
En el presente artículo se estimó el consumo específico de energía en el torneado de alta velocidad en seco del acero AISI 1045, utilizando redes neuronales. Se utilizaron varias arquitecturas de redes neuronales artificiales del tipo perceptrón multicapa, para establecer las relaciones entre los parámetros del régimen de corte y los índices tecnológicos de mecanizado. Se consideraron como magnitudes para la entrada de los modelos de redes neuronales, las siguientes: la velocidad de corte, la duración de la prueba, el tiempo de maquinado, el número de pasadas y la posición de la herramienta de corte sobre la probeta. El modelo de red neuronal seleccionado fue el mejor, según el error cuadrático medio y el coeficiente de regresión R2, reflejando una buena precisión en la aproximación. Los resultados evidenciaron un buen nivel de fiabilidad en la predicción del consumo específico de energía bajo diversas condiciones de mecanizado.
Palabras claves: consumo específico de energía; torneado de alta velocidad; AISI 1045; red neuronal artificial.
_________________________________________________________________________
Abstract
This article estimates the specific energy consumption in high-speed dry turning of AISI 1045 steel, using neural networks. Various artificial neural network architectures of the multilayer perceptron type were used to establish the relationships between the parameters of the cutting regime and the technological indices of machining. The following were considered as input values for the neural network models: the cutting speed, the test duration, the machining time, the number of passes and the position of the cutting tool on the specimen. The selected neural network model was the best, based on the mean square error and the regression coefficient R2, reflecting good precision in the approximation. The results showed a good level of reliability in predicting specific energy consumption under various machining conditions.Key words: specific energy consumption; high-speed dry turning; AISI 1045; artificial neural network.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).