An autonomous low-Cost infrared system for the on-line monitoring of manufacturing processes using novelty detection

This paper describes the implementation of a process monitoring system using a low-cost autonomous infrared imager combined with a novelty detection algorithm. The infrared imager is used to monitor the health of several manufacturing processes namely: drilling, grinding, welding and soldering. The main aim is to evaluate the use of low-cost infrared sensor technology combined with novelty detection to distinguish between normal and faulty conditions of manufacturing processes. The ultimate aim is to improve the reliability of the manufacturing operations so as to ensure high part quality and reduce inspection costs. The paper describes several case studies, which have shown that the new low-cost technology could provide an inexpensive and autonomous methodology for monitoring manufacturing processes. Novelty detection is used to compare normal and faulty conditions in order to provide an automated system for fault detection.

[1]  Kenneth A. Loparo,et al.  A decision fusion algorithm for tool wear condition monitoring in drilling , 2001 .

[2]  V. Radhakrishnan,et al.  On the Possibility of Process Monitoring in Grinding by Spark Intensity Measurements , 1994 .

[3]  Keith Worden,et al.  Long-term stability of normal condition data for novelty detection , 2000, Smart Structures.

[4]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[5]  Krzysztof Jemielniak,et al.  Commercial Tool Condition Monitoring Systems , 1999 .

[6]  Hans Kurt Tönshoff,et al.  Process Monitoring in Grinding Using Micromagnetic Techniques , 1999 .

[7]  Stephen J. Roberts,et al.  Extreme value statistics for novelty detection in biomedical signal processing , 2000 .

[8]  Emanuel Parzen,et al.  Stochastic Processes , 1962 .

[9]  YuMing Zhang,et al.  Precision Sensing of Arc Length in GTAW Based on Arc Light Spectrum , 2001 .

[10]  Florian Metze,et al.  Generalized radial basis function networks for classification and novelty detection: self-organization of optimal Bayesian decision , 2000, Neural Networks.

[11]  C.R.L. Murthy,et al.  Characteristics of AE signals obtained during drilling composite laminates , 2000 .

[12]  Jae Woong Youn,et al.  Detection of cutting tool fracture by dual signal measurements , 1994 .

[13]  Paul C. Nordine,et al.  Non-contact temperature measurement , 1991 .

[14]  Yildiz Bayazitoglu,et al.  Elements of Heat Transfer , 1988 .

[15]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[16]  Zhong Bing-lin,et al.  A study of on-line identification for grinding burn , 1992 .

[17]  K. F. Martin,et al.  A review by discussion of condition monitoring and fault diagnosis in machine tools , 1994 .

[18]  A. Al–Habaibeh,et al.  Self-Learning Algorithm for Automated Design of Condition Monitoring Systems for Milling Operations , 2001 .

[19]  T. I. El-Wardany,et al.  Tool condition monitoring in drilling using vibration signature analysis , 1996 .

[20]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[21]  Paul Conway,et al.  The application of IR thermography to process monitoring and control of reflow soldering , 1998 .

[22]  Stephen Malkin,et al.  Inverse heat transfer analysis of grinding, Part 1: Methods , 1996 .

[23]  R. Saunders.  THERMOCOUPLE ATTACHMENT FOR REFLOW SOLDER PROFILING AND PROCESS DEVELOPMENT , 1998 .