The multi-sensor-based measurement of machining signals and data fusion to develop predictive tool wear models for TiAlN-PVD coated carbide inserts during end milling of Inconel 617

Machining signals from the Force dynamometer, Acoustic Emission (AE), and Accelerometer are acquired and fused to develop Machine Learning (ML) models for tool wear monitoring of TiAlN-PVD coated carbide inserts. Milling experiments were performed on Inconel 617 with varied process parameter combina...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the Institution of Mechanical Engineers. Part B, Journal of engineering manufacture Journal of engineering manufacture, 2024-05, Vol.238 (6-7), p.886-903
Main Authors: Adishesha, Pramod, Lawrence K, Deepak, Mathew, Jose
Format: Article
Language:English
Subjects:
Accelerometers
Acoustic emission
Carbide tools
Data integration
Dynamometers
End milling
Inserts
Machine learning
Multisensor fusion
Nickel base alloys
Prediction models
Process parameters
Regression
Sensors
Superalloys
Support vector machines
Tool wear
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machining signals from the Force dynamometer, Acoustic Emission (AE), and Accelerometer are acquired and fused to develop Machine Learning (ML) models for tool wear monitoring of TiAlN-PVD coated carbide inserts. Milling experiments were performed on Inconel 617 with varied process parameter combinations until the tool flank wear met the failure criterion. Support Vector Regression, Random Forest Regression, and Long Short-Term Memory models are developed and compared based on a combination of sensor data fusion for tool wear predictions. It is observed that the Random Forest Regression approach can predict the tool wear with 94% accuracy compared to Support Vector Regression (85%) and Long Short-Term Memory (84%) models while using three-sensor data fusion. Further, the two-sensor data combination was used to test the relative efficacy of all the three developed machine learning tool wear models and found that the force dynamometer and the AE sensor fared better for Random Forest Regression and Long Short-Term Memory models in comparison to Support Vector Regression. For Support Vector Regression-based tool wear predictive models, force dynamometer and accelerometer data fusion performed better.
ISSN:0954-4054
2041-2975
DOI:10.1177/09544054231185155