TRC-2018 Learning Zone 46:50
by David Auton, C&W Services and Abhinav Khushraj, Petasense
After a successful pilot, C&W Services implemented a machine-learning based predictive maintenance system in order to address the limitations of a manual walk around program at one of its leading pharmaceutical client facility. Over the past year, by leveraging wireless sensors, secure cloud infrastructure and predictive analytics, C&W Services has been able to automate data collection, improve asset reliability, reduce equipment downtime, dramatically cut down on maintenance spend and achieve better resource allocation. Soon after deployment, the IIoT solution enabled the reliability engineers at C&W Services to detect a defect in an AHU, thereby preventing a catastrophic failure. The asset in question displayed an increase in the amplitude of fan shaft harmonics. Upon investigation, it was verified that the belts were running loose and the shafts were out of alignment. In another instance, the pillow block bearings were extremely noisy on the fan. There was a step increase in the acceleration spectrum, relatively small but noticeable that was returned to its normal vibration signature upon lubrication. With the continuous monitoring of critical rotating machinery, C&W Services has been able to achieve a competitive edge through a strong ROI along with other tangible benefits. Today it is inspiring others in the industrial world to make a transition towards IIoT.
“R.A.I.” the Reliability.aiTMChatbot
You can ask "R.A.I." anything about maintenance, reliability, and asset management.