Automated Predictive Maintenance Approach Listens to the Past

Grant Gerke | June 15, 2017

Fig. 1. The cavitation that caused this piston pump to fail catastrophically, to the point of melting the piston shoes, could have been detected weeks in advance through sound predictive maintenance.

The promise of automated predictive maintenance practices or condition monitoring seems like falling off a log by some solution providers, but the challenge is difficult with legacy systems and workflows. Also, most legacy plants are dealing with hybrid practices: part paper-based procedures and digital data coming from productions systems.

For manufacturers in modernization efforts, mountains of data is a real problem and especially when end users begin to implement automated predictive maintenance practices. Yeah, we have data but how do we act on it?

A new post by Annon Shenfield at IIoT World discusses the ability to fine-tune your automated predictive maintenance approach by recognizing the right “leading signals” and discusses the transition away from manual routines.

However, with automated PdM, a part of the intimate relationship between the technician and machine is broken, which makes understanding anomalies detected remotely very difficult.

Shenfield, the CEO of 3D Signals, discusses how sound can still be one of these go-to leading signals in automated Pd’M routine.

Sound as a leading signal for automated PdM enables detection and classification of a wide range of mechanical phenomena, often sooner than other sensing methods. This is due to the simple fact that moving parts – whether solid, liquid or gas – produce a unique sound pattern, and when something in that movement changes, even slightly, the sound produced changes too.