Demystifying the P-F Curve & Augmenting Machine Learning for Maintenance Optimization

P-F Curves are ubiquitous in the maintenance departments of industries, where it is used to explain the concept of an asset exhibiting symptoms of a failure before it experiences failure. This prognostication has been labeled as the effective way to plan maintenance programs. Though it is correct, the relentless push for its use using non-destructive prognostics tools has changed its meaning and interpretation by many end-users. Few curves are being drawn with 'vibration analysis' marked only in the region after a potential failure giving a misleading guide that this tool can be applied only after a failure has started. We are rescripting this by highlighting the fundamentals of the P-F Curve, as originally formulated, to train the readers for its use in everyday maintenance operations. The first half of the paper goes into detail on the foundations of the P-F Curve, the terms, and its definitions. It also briefs on how to choose the setup of these curves for an application. Following the steps described here will enable maintenance personnel to generate a P-F Curve and use the insight to plan maintenance work. The second half of the paper combines the fundamentals of the curves with Machine Learning techniques. This union of ideas is the natural extension of the way to push the boundaries of maintenance optimization. We describe how to supplement the traditional P-F Curve with Machine Learning by using the asset's performance data; to garner information in real time; to estimate its behavior; to use as feedback to improve the setup. This causes the curve to evolve into a dynamic plot and enhance the detection of failure by utilizing multiple parameters instead of a univariate. Finally, the pitfalls of using this new technology to support the P-F Curves is briefly discussed to serve as a caution to the user.