A GENERALIZED METHOD FOR FEATURIZATION OF MANUFACTURING SIGNALS, WITH APPLICATION TO TOOL CONDITION MONITORING

Published

August 5, 2017

Author(s)

Max Ferguson, Kincho Law, Raunak Bhinge, Yung-Tsun Lee

Abstract

The application of machine learning techniques in the manufacturing sector provides opportunities for increased production efficiency and product quality. In this paper, we describe how audio and vibration data from a sensor unit can be combined with machine controller data to predict the condition of a milling tool. Emphasis is placed on the generalizability of the method to a range of prediction tasks in a manufacturing setting. Time series audio and acceleration signals are collected from a Computer Numeric Control (CNC) milling machine and discretized into blocks. Fourier transform is employed to create generic power spectrum feature vectors. A Gaussian Process Regression model is then trained to predict the condition of the milling tool from the feature vectors. We highlight that this multi-step procedure could be useful for a range of manufacturing applications where the frequency content of a signal is related to a value of interest.

Proceedings Title

The 37th Computers and Information in Engineering Conference
IDETC2017

Conference Dates

August 6-9, 2017

Conference Location

Cleveland, OH, US

Pub Type

Conferences

Download Paper

Local Download

Keywords

Gaussian process regression, machine learning, manufacturing, tool condition

Citation

Ferguson, M. , Law, K. , Bhinge, R. and Lee, Y. (2017), A GENERALIZED METHOD FOR FEATURIZATION OF MANUFACTURING SIGNALS, WITH APPLICATION TO TOOL CONDITION MONITORING, The 37th Computers and Information in Engineering Conference IDETC2017, Cleveland, OH, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=922857 (Accessed December 12, 2024)