2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 12Citation - Scopus: 11Effect of Constitutive Material Model on the Finite Element Simulation of Shear Localization Onset(Elsevier, 2020) Yilmaz, Okan Deniz; Oliaei, Samad Nadimi BavilOne of the most challenging problems in the field of machining is to determine the onset of shear localization. The consequences of the emergence of shear localized chips are fluctuations in the machining forces, tool wear, deterioration of the surface quality and out-of-tolerance machined components. Several constitutive material models are developed for the simulation of shear localization during machining, especially for Ti6Al4V. However, the accuracy and capability of the proposed models for the prediction of shear localization onset have not been investigated yet. In this study, the effect of different constitutive material models in the prediction of shear localization onset has been investigated. Different material models are studied including the Johnson-Cook (J-C) material model with Cockcroft-Latham damage model, J-C material model with a J-C damage model, models based on modified J-C material models (MJ-C) with strain softening terms, and material model with power-law type strain hardening and strain rate sensitivity, with polynomial thermal softening and polynomial temperature-dependent damage. The results of the finite element models are verified using orthogonal cutting experiments in terms of chip morphology and machining forces. Metallography techniques are used along with SEM observations to elucidate the distinction between continuous and shear localized chips. The results of this study indicate that three models are capable of predicting shear localization onset. However, when compared to the experiments, where a critical cutting speed of 2.8 m/min is obtained for shear localization onset, the results revealed that the model proposed by Sima and Ozel (2016) which is a model based on MJ-C model with temperature-dependent overarching modifier and temperature-dependent material model parameters is more accurate for the prediction of shear localization onset during machining Ti6Al4V. This model is shown to reveal a good prediction for the machining forces as well.Article Citation - WoS: 1Citation - Scopus: 1Prediction of the Onset of Shear Localization Based on Machine Learning(Cambridge Univ Press, 2023) Akar, Samet; Ayli, Ece; Ulucak, Oguzhan; Ugurer, DorukPredicting the onset of shear localization is among the most challenging problems in machining. This phenomenon affects the process outputs, such as machining forces, surface quality, and machined part tolerances. To predict this phenomenon, analytical, experimental, and numerical methods (especially finite element analysis) are widely used. However, the limitations of each method hinder their industrial applications, demanding a reliable and time-saving approach to predict shear localization onset. Additionally, since this phenomenon largely depends on the type and parameters of the constitutive material model, any change in these parameters requires a new set of simulations, which puts further restrictions on the application of finite element modeling. This study aims to overcome the computational efficiency of the finite element method to predict the onset of shear localization when machining Ti6Al4V using machine learning methods. The obtained results demonstrate that the FCM (fuzzy c-means) clustering ANFIS (adaptive network-based fuzzy inference system) has given better results in both training and testing when it is compared to the ANN (artificial neural network) architecture with an R-2 of 0.9981. Regarding this, the FCM-ANFIS is a good candidate to calculate the critical cutting speed. To the best of the authors' knowledge, this is the first study in the literature that uses a machine learning tool to predict shear localization.
