Physics-informed Bayesian machine learning case study: Integral blade rotors

Corson, Gregory; Karandikar, Jaydeep; Schmitz, Tony

doi:10.1016/j.jmapro.2022.12.004

Physics-informed Bayesian machine learning case study: Integral blade rotors

Journal Article · Tue Dec 06 00:00:00 EST 2022 · Journal of Manufacturing Processes

DOI:https://doi.org/10.1016/j.jmapro.2022.12.004· OSTI ID:1908068

Corson, Gregory ^[1]; Karandikar, Jaydeep ^[2]; Schmitz, Tony ^[3]

Univ. of Tennessee, Knoxville, TN (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

This paper provides a physics-informed Bayesian machine learning (PIBML) description and case study. The PIBML approach applies three physics-based models to establish the initial beliefs before testing to determine the probability of milling stability (or prior). These include: receptance coupling substructure analysis (RCSA) prediction for the tool tip frequency response functions; finite element software prediction of the mechanistic force model coefficients; and a spindle speed-dependent power law model for process damping. Testing was then performed to identify optimal stable machining conditions using an expected improvement in material removal rate criterion. The prior probability of stability was updated using the test results to determine the posterior probability of stability. The test results were compared to the parameter recommendations provided by the endmill manufacturer. A demonstration integral blade rotor was machined at the optimal stable machining conditions for 304 stainless steel and 6061-T6 aluminum. Finally, the disagreement between manufacturer recommendations and milling performance in both materials tested emphasizes the need for broad implementation of PIBML approaches to increase machining productivity and efficiency.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1908068

Journal Information:: Journal of Manufacturing Processes, Journal Name: Journal of Manufacturing Processes Journal Issue: 1 Vol. 85; ISSN 1526-6125

Publisher:: Society of Manufacturing Engineers; ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (31)

Updated semi-discretization method for periodic delay-differential equations with discrete delay Insperger, Tamás; Stépán, Gábor International Journal for Numerical Methods in Engineering, Vol. 61, Issue 1 https://doi.org/10.1002/nme.1061	journal	August 2004
Ensemble transfer learning for refining stability predictions in milling using experimental stability states Postel, M.; Bugdayci, B.; Wegener, K. The International Journal of Advanced Manufacturing Technology, Vol. 107, Issue 9-10 https://doi.org/10.1007/s00170-020-05322-w	journal	April 2020
Analysis of tool wear effect on chatter stability in turning Chiou, Y. S.; Chung, E. S.; Liang, S. Y. International Journal of Mechanical Sciences, Vol. 37, Issue 4 https://doi.org/10.1016/0020-7403(94)00070-Z	journal	April 1995
Numerical simulation of non-linear chatter vibration in turning Jemielniak, Krzysztof; Widota, Adam International Journal of Machine Tools and Manufacture, Vol. 29, Issue 2 https://doi.org/10.1016/0890-6955(89)90035-7	journal	January 1989
Modeling of the process damping force in chatter vibration Lee, B. Y.; Tarng, Y. S.; Ma, S. C. International Journal of Machine Tools and Manufacture, Vol. 35, Issue 7 https://doi.org/10.1016/0890-6955(94)00046-M	journal	July 1995
Analytical Prediction of Stability Lobes in Milling Altintaş, Y.; Budak, E. CIRP Annals, Vol. 44, Issue 1 https://doi.org/10.1016/S0007-8506(07)62342-7	journal	January 1995
On the Dynamics of High-Speed Milling with Long, Slender Endmills Davies, M. A.; Dutterer, B.; Pratt, J. R. CIRP Annals, Vol. 47, Issue 1 https://doi.org/10.1016/S0007-8506(07)62784-X	journal	January 1998
The Stability of Low Radial Immersion Milling Davies, M. A.; Pratt, J. R.; Dutterer, B. S. CIRP Annals, Vol. 49, Issue 1 https://doi.org/10.1016/S0007-8506(07)62891-1	journal	January 2000
Predicting High-Speed Machining Dynamics by Substructure Analysis Schmitz, T. L.; Donalson, R. R. CIRP Annals, Vol. 49, Issue 1 https://doi.org/10.1016/S0007-8506(07)62951-5	journal	January 2000
On the dynamics of ball end milling: modeling of cutting forces and stability analysis Abrari, F.; Elbestawi, M. A.; Spence, A. D. International Journal of Machine Tools and Manufacture, Vol. 38, Issue 3 https://doi.org/10.1016/S0890-6955(97)00039-4	journal	February 1998
Chatter stability of a slender cutting tool in turning with tool wear effect Chiou, Richard Y.; Liang, Steven Y. International Journal of Machine Tools and Manufacture, Vol. 38, Issue 4 https://doi.org/10.1016/S0890-6955(97)00079-5	journal	March 1998
Identification of dynamic cutting force coefficients and chatter stability with process damping Altintas, Y.; Eynian, M.; Onozuka, H. CIRP Annals, Vol. 57, Issue 1 https://doi.org/10.1016/j.cirp.2008.03.048	journal	January 2008
Online adaption of milling parameters for a stable and productive process Bergmann, Benjamin; Reimer, Svenja CIRP Annals, Vol. 70, Issue 1 https://doi.org/10.1016/j.cirp.2021.04.086	journal	January 2021
Machining chatter in flank milling Ahmadi, K.; Ismail, F. International Journal of Machine Tools and Manufacture, Vol. 50, Issue 1 https://doi.org/10.1016/j.ijmachtools.2009.09.005	journal	January 2010
Experimental investigation of process damping nonlinearity in machining chatter Ahmadi, K.; Ismail, F. International Journal of Machine Tools and Manufacture, Vol. 50, Issue 11 https://doi.org/10.1016/j.ijmachtools.2010.07.002	journal	November 2010
Physics-informed Bayesian inference for milling stability analysis Chen, Gengxiang; Li, Yingguang; Liu, Xu International Journal of Machine Tools and Manufacture, Vol. 167 https://doi.org/10.1016/j.ijmachtools.2021.103767	journal	August 2021
Analytical process damping stability prediction Tyler, Christopher T.; Schmitz, Tony L. Journal of Manufacturing Processes, Vol. 15, Issue 1 https://doi.org/10.1016/j.jmapro.2012.11.006	journal	January 2013
Stability boundary and optimal operating parameter identification in milling using Bayesian learning Karandikar, Jaydeep; Honeycutt, Andrew; Schmitz, Tony Journal of Manufacturing Processes, Vol. 56 https://doi.org/10.1016/j.jmapro.2020.04.019	journal	August 2020
Dynamics of 2-dof regenerative chatter during turning Chandiramani, N. K.; Pothala, T. Journal of Sound and Vibration, Vol. 290, Issue 1-2 https://doi.org/10.1016/j.jsv.2005.04.012	journal	February 2006
Radial depth of cut stability lobe diagrams with process damping effects Tyler, Christopher T.; Troutman, John; Schmitz, Tony L. Precision Engineering, Vol. 40 https://doi.org/10.1016/j.precisioneng.2014.11.004	journal	April 2015
Milling stability identification using Bayesian machine learning Karandikar, Jaydeep; Honeycutt, Andrew; Smith, Scott Procedia CIRP, Vol. 93 https://doi.org/10.1016/j.procir.2020.04.022	journal	January 2020
Analysis of different machine learning algorithms to learn stability lobe diagrams Denkena, Berend; Bergmann, Benjamin; Reimer, Svenja Procedia CIRP, Vol. 88 https://doi.org/10.1016/j.procir.2020.05.049	journal	January 2020
A Bayesian Framework for Milling Stability Prediction and Reverse Parameter Identification Cornelius, Aaron; Karandikar, Jaydeep; Gomez, Michael Procedia Manufacturing, Vol. 53 https://doi.org/10.1016/j.promfg.2021.06.073	journal	January 2021
Bayesian uncertainty quantification and propagation for prediction of milling stability lobe Li, Kai; He, Songping; Liu, Hongqi Mechanical Systems and Signal Processing, Vol. 138 https://doi.org/10.1016/j.ymssp.2019.106532	journal	April 2020
Stability of Interrupted Cutting by Temporal Finite Element Analysis Bayly, P. V.; Halley, J. E.; Mann, B. P. Journal of Manufacturing Science and Engineering, Vol. 125, Issue 2 https://doi.org/10.1115/1.1556860	journal	April 2003
Three-Component Receptance Coupling Substructure Analysis for Tool Point Dynamics Prediction Schmitz, Tony L.; Duncan, G. Scott Journal of Manufacturing Science and Engineering, Vol. 127, Issue 4 https://doi.org/10.1115/1.2039102	journal	February 2005
Mechanistic Modeling of Process Damping in Peripheral Milling Huang, C. Y.; Wang, J. J. Junz Journal of Manufacturing Science and Engineering, Vol. 129, Issue 1 https://doi.org/10.1115/1.2335857	journal	March 2006
Modelling Machining Dynamics Including Damping in the Tool-Workpiece Interface Elbestawi, M. A.; Ismail, F.; Du, R. Journal of Engineering for Industry, Vol. 116, Issue 4 https://doi.org/10.1115/1.2902125	journal	November 1994
A New Approach of Formulating the Transfer Function for Dynamic Cutting Processes Wu, D. W. Journal of Engineering for Industry, Vol. 111, Issue 1 https://doi.org/10.1115/1.3188730	journal	February 1989
An Explanation of Low-Speed Chatter Effects Sisson, T. R.; Kegg, R. L. Journal of Engineering for Industry, Vol. 91, Issue 4 https://doi.org/10.1115/1.3591778	journal	November 1969
Machining Forces: Some Effects of Tool Vibration Wallace, P. W.; Andrew, C. Journal of Mechanical Engineering Science, Vol. 7, Issue 2 https://doi.org/10.1243/JMES_JOUR_1965_007_023_02	journal	June 1965

Similar Records

Review and status of tool tip frequency response function prediction using receptance coupling

Journal Article · Fri Sep 30 20:00:00 EDT 2022 · Precision Engineering · OSTI ID:1892405

Milling stability identification using Bayesian machine learning

Conference · Wed Jul 01 00:00:00 EDT 2020 · OSTI ID:2205462

A Bayesian Framework for Milling Stability Prediction and Reverse Parameter Identification

Conference · Thu Jul 01 00:00:00 EDT 2021 · OSTI ID:1808387

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
blisk
machine learning
milling
stability

Physics-informed Bayesian machine learning case study: Integral blade rotors

Citation Formats

References (31)

Similar Records

Related Subjects