RESUMO
The computer numerical control (CNC) machine has recently taken a fundamental role in the manufacturing industry, which is essential for the economic development of many countries. Current high quality production standards, along with the requirement for maximum economic benefits, demand the use of tool condition monitoring (TCM) systems able to monitor and diagnose cutting tool wear. Current TCM methodologies mainly rely on vibration signals, cutting force signals, and acoustic emission (AE) signals, which have the common drawback of requiring the installation of sensors near the working area, a factor that limits their application in practical terms. Moreover, as machining processes require the optimal tuning of cutting parameters, novel methodologies must be able to perform the diagnosis under a variety of cutting parameters. This paper proposes a novel non-invasive method capable of automatically diagnosing cutting tool wear in CNC machines under the variation of cutting speed and feed rate cutting parameters. The proposal relies on the sensor information fusion of spindle-motor stray flux and current signals by means of statistical and non-statistical time-domain parameters, which are then reduced by means of a linear discriminant analysis (LDA); a feed-forward neural network is then used to automatically classify the level of wear on the cutting tool. The proposal is validated with a Fanuc Oi mate Computer Numeric Control (CNC) turning machine for three different cutting tool wear levels and different cutting speed and feed rate values.
Assuntos
Fenômenos Mecânicos , Redes Neurais de Computação , AcústicaRESUMO
RESUMEN El objetivo de esta investigación es determinar los valores de velocidad de corte, avance y trayectoria (estrategia de mecanizado) en el mecanizado del PEEK que permitan obtener una rugosidad (Ra) recomendada según la literatura para la adecuada diferenciación, proliferación y adhesión de células mesenquimales aplicables en implantes óseos[3,4,6,7,11]. De la revisión del estado del arte se determinó que dichos procesos celulares se obtienen cuando la rugosidad superficial Ra tiene un valor entre 1 μm a 3 μm[9,12], de igual forma, a mayor anisotropía superficial, mayor diferenciación celular se obtendrá[7,8]. Para determinar los parámetros de corte con los que se obtiene una rugosidad Ra óptima se realizó un diseño experimental de superficie de respuesta con rangos de exploración de: velocidad de corte: 60 m/min - 90 m/min y velocidad de avance: 900 mm/min - 1500 mm/min usados para ambas estrategias evaluadas: Raster y Espiral. La investigación concluyó que los parámetros de mecanizado con los cuales se obtiene una rugosidad recomendada Ra para la elaboración de implantes óseos son: velocidad de avance 1500 mm/min y velocidad de corte de 90 m/min mecanizando con una trayectoria (técnica de mecanizado) Raster, con la cual se obtiene una rugosidad Ra de 2,7 μm.
ABSTRACT The objective of this study is determinate the values of cutting speed, feed along and the machining strategy to get optimal values of roughness Ra for the machining of PEEK, polyetheretherketone, to get to get differentiation, proliferation and adhesion for mesenchymal for the development of individualized tailored prosthesis. According to literature to get those cellular process the superficial roughness must have a value Ra of 1 μm to 3 μm, also, if more anisotropic surface, more adhesion of cells. To determinate the recommended roughness Response Surface Methodology was used, the region of operability was: cutting speed 60 m/min to 90 m/min, feed along 900 mm/min to 1500 mm/min and a cutting strategy of Raster and Spiral. In this investigation the conclusion was that the cutting parameter to get the recommended roughness Ra for the elaboration of tailored prosthesis is feed along of 1500 mm/min and cutting speed of 90 m/min, machining with Raster strategy, for those parameters the roughness was of 2,7 μm.