Publicación: Aplicación de herramientas de Inteligencia Artificial para la optimización frente al gripado del contenido de aditivos FM, EP y AW en un lubricante
Fecha
2022
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España), Universidad Politécnica de Madrid. Departamento de Ingeniería Mecánica
Resumen
Este trabajo presenta una metodología para correlacionar la concentración de aditivos modificadores de fricción (FM), extrema presión (EP) y anti desgaste (AW) en un lubricante con su comportamiento de fricción en un ensayo de scuffing mediante el uso de herramientas de Inteligencia Artificial (IA). Para ello, se ha integrado una gran cantidad de información procedente de estudios experimentales previos sobre scuffing y valores propios experimentales de fricción, obtenidos en una Mini-Máquina de Tracción (MTM), con aceites que contienen diferentes concentraciones de aditivos. Con la información seleccionada se ha contrastado la eficacia y fiabilidad de la predicción con dos herramientas de IA: RNA (Red Neuronal Artificial) y SVM (Máquina de Soporte Vectorial). Los parámetros de creación y entrenamiento de las herramientas se han seleccionado de forma que se obtenga un valor de correlación que supere el 98 % para ambos casos. Posteriormente, en una segunda fase, se aplica la predicción de la concentración óptima de aditivo del lubricante que mejora la resistencia del lubricante al scuffing.
This paper presents a methodology to correlate the concentration of friction modifier (FM), extreme pressure (EP) and anti-wear (AW) additives in a lubricant with its friction behavior in a scuffing test by using Artificial Intelligence (AI) tools. For this purpose, we have integrated a large amount of information from previous experimental studies on scuffing and our own experimental friction values obtained in a Mini-Traction Machine (MTM) with oils containing different concentrations of additives. With the selected information, the efficiency and reliability of the prediction has been contrasted with two AI tools: ANN (Artificial Neural Network) and SVM (Support Vector Machine). The creation and training parameters of the tools have been selected in such a way as to obtain a correlation value exceeding 98% for both cases. Subsequently, in a second phase, the prediction of the optimum concentration of lubricant additive that improves the lubricant's resistance to scuffing was applied.
This paper presents a methodology to correlate the concentration of friction modifier (FM), extreme pressure (EP) and anti-wear (AW) additives in a lubricant with its friction behavior in a scuffing test by using Artificial Intelligence (AI) tools. For this purpose, we have integrated a large amount of information from previous experimental studies on scuffing and our own experimental friction values obtained in a Mini-Traction Machine (MTM) with oils containing different concentrations of additives. With the selected information, the efficiency and reliability of the prediction has been contrasted with two AI tools: ANN (Artificial Neural Network) and SVM (Support Vector Machine). The creation and training parameters of the tools have been selected in such a way as to obtain a correlation value exceeding 98% for both cases. Subsequently, in a second phase, the prediction of the optimum concentration of lubricant additive that improves the lubricant's resistance to scuffing was applied.
Descripción
Categorías UNESCO
Palabras clave
aditivos FM, AW y EP, gripado, Inteligencia Artificial, lubricación
Citación
Centro
E.T.S. de Ingenieros Industriales
Departamento
Mecánica