000163108 001__ 163108
000163108 005__ 20251024170832.0
000163108 0247_ $$2doi$$a10.1016/j.engappai.2025.112180
000163108 0248_ $$2sideral$$a145551
000163108 037__ $$aART-2025-145551
000163108 041__ $$aeng
000163108 100__ $$0(orcid)0000-0001-8689-6482$$aAguado, Sergio$$uUniversidad de Zaragoza
000163108 245__ $$aSurface roughness prediction in turning processes for grey cast iron: A hybrid machine learning approach integrating infrared thermography
000163108 260__ $$c2025
000163108 5060_ $$aAccess copy available to the general public$$fUnrestricted
000163108 5203_ $$aWorkpiece surface quality is a critical control parameter in machining processes, influencing functional performance, dimensional precision, and wear resistance. However, accurately predicting surface roughness is complex, often limited by the computational demands of traditional high-precision methods and the reliance of existing models solely on cutting parameters, hindering real-time monitoring. This research introduces a hybrid Artificial Neural Network (ANN) methodology specifically developed for predicting surface roughness of grey cast iron GG-25 workpieces machined in turning processes, a material previously unstudied in this context. The methodology integrates real-time infrared thermal measurements from multiple defined regions of interest (ROIs) within the tool-workpiece contact zone, along with cutting parameters.
Experimental results demonstrated that feed rate (f) is the most significant cutting parameter (effect = 0.43) affecting surface quality, followed by its combination with cutting speed (Vc) (effect = −0.25) and cutting speed (effect = 0.18). Correlation and non-linear regression analyses revealed complex, often exponential relationships between temperature and surface roughness, showing temperature an upward trend as machining progressed. The developed ANN achieves a correlation coefficient (R) value of 0.99 both when predicting the roughness arithmetic mean deviation (Ra) parameter in training conditions and when using data from experiments not used in training (validations data). Moreover, the model reaches a correlation coefficient value of 0.85 (test data) under cutting conditions different from those used in experiments, demonstrating robustness, significantly outperforming Support Vector Regression (SVR). This model represents a highly potential tool for real-time online inspection.
000163108 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T56-17R$$9info:eu-repo/grantAgreement/ES/MINECO/PID2021-125530OB-I00
000163108 540__ $$9info:eu-repo/semantics/embargoedAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000163108 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000163108 700__ $$0(orcid)0000-0002-4931-8752$$aPueo, Marcos$$uUniversidad de Zaragoza
000163108 700__ $$0(orcid)0000-0002-4917-8550$$aAcero, Raquel$$uUniversidad de Zaragoza
000163108 700__ $$0(orcid)0000-0002-3945-2595$$aMajarena, Ana Cristina$$uUniversidad de Zaragoza
000163108 700__ $$0(orcid)0000-0001-7316-0003$$aSantolaria, Jorge$$uUniversidad de Zaragoza
000163108 7102_ $$15002$$2305$$aUniversidad de Zaragoza$$bDpto. Ingeniería Diseño Fabri.$$cÁrea Expresión Gráfica en Ing.
000163108 7102_ $$15002$$2515$$aUniversidad de Zaragoza$$bDpto. Ingeniería Diseño Fabri.$$cÁrea Ing. Procesos Fabricación
000163108 773__ $$g161 (2025), 112180 [16 pp.]$$pEng. appl. artif. intell.$$tENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE$$x0952-1976
000163108 8564_ $$s1943162$$uhttps://zaguan.unizar.es/record/163108/files/texto_completo.pdf$$yPostprint$$zinfo:eu-repo/date/embargoEnd/2027-09-10
000163108 8564_ $$s2833820$$uhttps://zaguan.unizar.es/record/163108/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint$$zinfo:eu-repo/date/embargoEnd/2027-09-10
000163108 909CO $$ooai:zaguan.unizar.es:163108$$particulos$$pdriver
000163108 951__ $$a2025-10-24-17:02:48
000163108 980__ $$aARTICLE