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

Gregory Corson, Jaydeep Karandikar, Tony Schmitz

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

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. 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.

Original languageEnglish
Pages (from-to)503-514
Number of pages12
JournalJournal of Manufacturing Processes
Volume85
DOIs
StatePublished - Jan 6 2023

Funding

This research was supported by MxD project number 20-11-04 Physics-Guided Machine Learning (PGML) for CNC Milling. This material is based on research sponsored by Office of the Under Secretary of Defense for Research and Engineering, Strategic Technology Protection and Exploitation, Defense Manufacturing Science and Technology Program under agreement number W15QKN-19-3-0003 between MxD and the Government. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes.

FundersFunder number
Defense Manufacturing Science and Technology ProgramW15QKN-19-3-0003
Office of the Under Secretary of Defense for Research and Engineering, Strategic Technology Protection and Exploitation

    Keywords

    • Blisk
    • Machine learning
    • Milling
    • Stability

    Fingerprint

    Dive into the research topics of 'Physics-informed Bayesian machine learning case study: Integral blade rotors'. Together they form a unique fingerprint.

    Cite this