Asset management: listening to your asset

Abstract

The ability to measure large amounts of data at high frequency, and the increasing ability to process these data close to the source at the edge, has opened up a new frontier in asset management. Until now, analysis of high-frequency data in real time has been the domain of a few, very expensive devices. However, this is rapidly changing, with the increasing capabilities of sensors and edge devices providing flexible, low-cost solutions that can be deployed across all site machinery to provide predictive and detailed information about these assets. All machinery vibrates at multiple frequencies when running. If you listen to this vibration, it can tell you a lot about the condition of the machine and its components. In fact, it is surprising how rich and detailed this information can be. Cavitation, insufficient lubrication, failing bearings and faulty impellers all have different vibration signatures, and by listening for these signatures it is possible to identify issues before they occur, and even predict when they will occur. It is also possible to feed this information (e.g. cavitation) to the control system so that process decisions can be made to avoid machine damage. This paper discusses solutions that are available now and currently being developed in terms of edge computing devices and advances in the algorithms that analyse the vibration data, and how they can be applied in the oil and gas industry to ensure assets are optimised and downtime is minimised.