Comparative Assessment of the Force Prediction Abilities of Some Single Edge Orthogonal Cutting Models over Diverse Data

• Published in: Machining science and technology Vol. 8; no. 1; pp. 53 - 84
• Main Authors: Venuvinod, Patri K., Cheng, M. K.
• Format: Journal Article
• Language: English
• Published: Philadelphia, PA Taylor & Francis Group 30.12.2004; Taylor & Francis
• Subjects: Applied sciences; Cutting force prediction; Exact sciences and technology; Machining models; Mechanical engineering. Machine design; Orthogonal cutting; Shear angle prediction; Cutting force prediction; Data analysis; Empirical method; Machining; Neural network; Modeling; Machining models; Shear angle prediction; Analytical method; Root mean square value; Orthogonal cutting; Thrust; Cutting force
• ISSN: 1091-0344; 1532-2483
• DOI: 10.1081/MST-120034241

The relative force prediction abilities of some well-known ANN-based, empirical and analytical models are assessed against several independent datasets by taking the rms error of cutting and thrust forces over all the datasets as the criterion. Progressing beyond mere data analysis, attention is paid to issues concerning how the model parameters themselves could be numerically modeled. A methodology for avoiding the need for measuring the shear angle, φ, is also developed. Model coefficients are estimated through nonlinear constrained optimization techniques. For estimating φ, the fractional variation of an idealized material invariant such as the mean shear stress, τ, on the shear plane is minimized subject to Hill's classical constraints. Several hitherto unknown insights regarding the relative effectiveness of each of the models have emerged. For example, it is found that the φ-values estimated from the measured forces alone are superior to those determined from chip measurements in the traditional manner.