ORIGINAL ARTICLE An autonomous low-Cost infrared system for the on-line monitoring of manufacturing processes using novelty detection Received: 27 March 2002 / Accepted: 26 June 2002 / Published online: 18 June 2003 Ó Springer-Verlag London Limited 2003 Abstract 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: dril- ling, 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 pro- cesses. 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 manufactur- ing processes. Novelty detection is used to compare normal and faulty conditions in order to provide an automated system for fault detection. Keywords Infrared Æ condition monitoring Æ manufacturing processes Æ welding Æ grinding Æ drilling Æ soldering Æ novelty detection 1 Introduction The international competition and increasing require- ments for high quality and low cost has increased the unpredictability of surroundings creating an urgent need for implementing new technologies and utilising existing commercial technologies as a vital approach for indus- trial survival. Condition monitoring of manufacturing operations is an important strategy to be implemented. It offers a flexible, effective and economical tool to im- prove the entire performance of manufacturing systems through: better design; enhanced health and safety standards; the minimisation of unproductive time of staff; improved quality and reliability; minimum envi- ronmental pollution; the improved availability of ma- chine tools; better customer satisfaction; maximum profits and the optimised quality of the manufactured products [1]. Productivity can also be improved by including the necessary inspection and quality control processes within the production stage. What is needed is an automated process condition monitoring system that predicts failures before they cause damage or breakdown [2]. Condition-monitoring systems should be able to track process faults, which can offer the highest potential for avoiding unproductive down-time and maintain the highest quality of the manufactured products. Many different types of sensors and signal processing methods are now commercially available for monitoring manufacturing processes [3]. Many ideas have been presented and numerous approaches have been pro- posed for condition monitoring. Manufacturing pro- cesses, in general, and machining processes, in particular, are difficult to monitor due to the high combinations of operating conditions and faults. To fully understand and attempt to control the behaviour of machine tools and the manufacturing processes, effective condition monitoring systems should be developed which guarantee the reliability of the system operations and the quality of products [4]. Multiple sensors have been beneficially implemented in complex manufactur- ing condition monitoring systems to obtain compre- hensive information about the process [5]. The utilisation of different sensors involves integration and fusion of the sensory signals to extract the key features from the data by removing any existing redundancy. Many different types of sensors are now commercially available coupled with signal processing methods. Sen- sors are key elements of a successful monitoring system [3]. Sensors far as force, acoustic emission (AE), vibra- tions and the conventional visible spectrum camera [5,6] and infrared cameras for monitoring the heat patterns or Int J Adv Manuf Technol (2003) 22: 249–258 DOI 10.1007/s00170-002-1467-z Amin Al-Habaibeh Æ Robert Parkin A. Al-Habaibeh (&) Æ R. Parkin Mechatronics Research Centre, Wolfson School of Mechanical and Manufacturing Engineering, Loughborough University, LE11 3TU, UK E-mail: a.al-habaibeh@lboro.ac.uk