A Generalized Method for Featurization of Manufacturing Signals, With Application to Tool Condition Monitoring

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 transformation 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. INTRODUCTION The application of modern machine learning techniques to manufacturing processes provides an opportunity to increase productivity and improve overall product quality in traditional manufacturing lines [1]. The adoption of predictive models within the industrial value chain is part of a larger transition often referred to as the industrial internet, which promises to bring substantially increased operational effectiveness as well as the development of entirely new business models, services, and products [2]. In order to increase manufacturing productivity while reducing maintenance costs, it is crucial to develop more intelligent maintenance strategies, that can predict when maintenance should be performed [3]. Reliable tool-condition monitoring is likely to play an important role in the reactive maintenance strategies of future manufacturing facilities.

[1]  Anselmo Eduardo Diniz,et al.  Correlating tool life, tool wear and surface roughness by monitoring acoustic emission in finish turning , 1992 .

[2]  Joseph M. Romano,et al.  Dimensional Reduction of High-Frequency Accelerations for Haptic Rendering , 2010, EuroHaptics.

[3]  Robert X. Gao,et al.  Deep Learning and Its Applications to Machine Health Monitoring: A Survey , 2016, ArXiv.

[4]  D. E. Dimla,et al.  Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods , 2000 .

[5]  Wai-Ki Ching,et al.  Detection of machine failure: Hidden Markov Model approach , 2009, Comput. Ind. Eng..

[6]  Jan Peters,et al.  Local Gaussian process regression for real-time model-based robot control , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  D. E. Dimla,et al.  Neural network solutions to the tool condition monitoring problem in metal cutting—A critical review of methods , 1997 .

[8]  David Dornfeld,et al.  A study of tool wear using statistical analysis of metal-cutting acoustic emission , 1982 .

[9]  Kincho H. Law,et al.  Evaluation of a PMML-based GPR scoring engine on a cloud platform and microcomputer board for smart manufacturing , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[10]  Boris Otto,et al.  Design Principles for Industrie 4.0 Scenarios , 2016, 2016 49th Hawaii International Conference on System Sciences (HICSS).

[11]  John Hallam,et al.  Novel Automatic Filter-Class Feature Selection for Machine Learning Regression , 2016, INNS Conference on Big Data.

[12]  Connor Jennings,et al.  A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests , 2017 .

[13]  Sudarsan Rachuri,et al.  A Generalized Data-Driven Energy Prediction Model With Uncertainty for a Milling Machine Tool Using Gaussian Process , 2015 .

[14]  Kincho H. Law,et al.  An intelligent machine monitoring system for energy prediction using a Gaussian Process regression , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[15]  László Monostori.  AI and machine learning techniques for managing complexity, changes and uncertainties in manufacturing , 2002 .

[16]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[17]  Monson H. Hayes,et al.  Statistical Digital Signal Processing and Modeling , 1996 .

[18]  C. Sanjay,et al.  Modeling of tool wear in drilling by statistical analysis and artificial neural network , 2005 .

[19]  F. Moon,et al.  Nonlinear models for complex dynamics in cutting materials , 2001, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[20]  Rui Silva,et al.  TOOL WEAR MONITORING OF TURNING OPERATIONS BY NEURAL NETWORK AND EXPERT SYSTEM CLASSIFICATION OF A FEATURE SET GENERATED FROM MULTIPLE SENSORS , 1998 .

[21]  K H Law,et al.  Gaussian Process Regression (GPR) Representation in Predictive Model Markup Language (PMML). , 2017, Smart and sustainable manufacturing systems.

[22]  Charu C. Aggarwal,et al.  Feature Selection for Classification: A Review , 2014, Data Classification: Algorithms and Applications.

[23]  Dan Braha.  Data mining for design and manufacturing: methods and applications , 2001 .