Machine Condition Detection For Milling Operations Using Low Cost Ambient Sensors
Anantha Narayanan Narayanan, Alec Kanyuck, Satyandra K. Gupta, Sudarsan Rachuri
In recent years, sensor technology and data mining capabilities have advanced greatly, allowing advanced manufacturing enterprises to closely monitor their manufacturing operations. Conditions such as tool breakage and tool wear can be predicted by analyzing data collected from sensors mounted on machines and tools. At the same time, a thriving market has developed for low cost consumer level sensors and processors. A proliferation of low cost sensing hardware, combined with the availability of free and open source software for performing data analytics, provides a new opportunity for manufacturers. These software and hardware tools are relatively inexpensive, and require limited expertise for installation and use. Older machines can be retrofitted with new sensors. Yet, these tools have not been investigated deeply in the manufacturing world. In this work, we use a combination of low cost sensing hardware and free and open source software to monitor a milling machine operation. We use the data collected from the sensors to determine the operating condition of the machine, and to detect any anomaly in the machine operation. If successfully applied, these techniques will be very valuable for small manufacturers, to determine key factors such as machine utilization, or to detect catastrophic failures early during machining.
Proceedings of the ASME 2016 Manufacturing Science and Engineering Conference (MSEC2016)
June 27-July 1, 2016
The ASME 2016 Manufacturing Science and Engineering Conference (MSEC2016)
, Kanyuck, A.
, Gupta, S.
and Rachuri, S.
Machine Condition Detection For Milling Operations Using Low Cost Ambient Sensors, Proceedings of the ASME 2016 Manufacturing Science and Engineering Conference (MSEC2016)
, Blacksburg, VA
(Accessed November 28, 2023)