Remote acoustic analysis for tool condition monitoring

Within the manufacturing industry, predictive maintenance is a well-established concept, dating back to the 1990's [1]. Practice has shown it to have a proven track record of minimising unnecessary machine downtime. The methods of predictive maintenance have varied widely, including visual inspection (i.e. human monitoring), thermal imaging, ultrasonic analysis, vibration analysis, power consumption, acoustic emission, to name a few. As manufacturing technologies have developed, maintenance in general has become a more complex task, presenting many challenges for researchers, engineers and scientists. These challenges have been met through research and development of new technologies and methods of maintenance. Some of these methods currently involve installing intricate sensor systems which are placed on, or in close proximity to the system under test (SUT). Although some of these monitoring methods have been slow to catch on within industry, much of the reason for this can be accredited to the high cost of these sensors along with the high probability of damage to and the replacement of them. Practice is now moving towards using remote monitoring systems (RMS) as a possible method to reduce some of these issues. This is due to the ability to carry out monitoring without having to install the monitoring system on the structure of the SUT, hence minimising the potential for damage to the sensor systems. This paper aims to describe the importance of predictive maintenance (PdM) over other maintenance methods (e.g. reactive, corrective etc.), the importance of PdM for the metal cutting industry (focusing on cutting tool wear), while also discussing some common methods of predictive maintenance monitoring system methods already being utilised within industry. The final method discussed is remote monitoring systems used to monitor transmitted sound, while also identifying how this monitoring system could be integrated within the smart manufacturing environment that is being driven by Industry 4.0. (C) 2019 The Authors. Published by Elsevier B.V.