The curve shows that as a failure starts manifesting, the equipment deteriorates to the point at which it can possibly be detected (point “P”). If the failure is not detected and mitigated, it continues until a functional failure occurs (point “F”). The time range between P and F, commonly called the P-F interval, is the window of opportunity during which an inspection can possibly detect the imminent failure and give a time & opportunity for maintenance personnel to address it.
A common rule of thumb is that the interval between CBM tasks should be one-half or one-third of the P-F interval. Effectiveness of CBM depends on how long the P-F interval is. Failure modes where the P-F interval shows a large variability, condition monitoring is not an effective strategy. With plenty of warning, the rectification can be planned, materials and resources can be mobilized, and breakdown prevented (though production is still stopped for the maintenance duration). When the P-F interval is only a few days, the resulting organizational and workplace actions are much like a breakdown and the value of CBM is largely lost.
It is important to realize that CBM as a maintenance strategy does not reduce the likelihood of a failure occurring through life-renewal, but instead is aimed at intervening before the failure occurs, on the premise that this is more economical and should have less of an impact on availability. An efficient and effective process for data gathering, data analysis, decision making, and finally, early intervention, is critical for the success of CBM.
Most organizations have either adopted or evaluated one or more of the techniques discussed above to predict or prevent failures. While such techniques enhance asset performance, we believe it is critical to prescribe a relationship between the operation window and the failure type using analytics and data science, and find a more robust approach in order to understand the reasons behind the problems leading to the failures.
Every equipment has an operating range to cope with alterations/variations in operating conditions like flow, pressure, temperature etc. Overlaying, the thermodynamic equation of the equipment over the failure prediction generated from above techniques, based on the level of operation; operators can try to define the particular operating level and set certain target points. Since we know every equipment has an operating range to cope with alterations/variations in operating conditions like flow, pressure, temperature etc. and by calculating the thermodynamic equation, we can decide the prediction failure type based on the level of operation. Operators can then try to define the particular operating level for particular predictive fail, set to certain target points. The goal is to play with the operating window to maintain the demand either (surge or reduce) based on insights collected from collaboration with multiple sources.
When a change in the data related to any equipment/asset occurs, Prescriptive Maintenance (PM) will let us evaluate when and where failure is going to happen but also why it is happening. The reason behind the failure helps the PM identify different options and the potential outcomes to mitigate any risk to the operation along with the probability of success. With this information, the PM can prescribe the operating level to manage the lifespan of the equipment. This is a paradigm shift from current industry initiatives around Asset Performance Management and only a handful of organizations have already started experimenting with the technique for their critical equipment.
We have observed that APM can be leveraged beyond managing the Safety monitoring and Maintenance purpose for asset-intensive organizations but it can also generate information that propels business decisions. Every decision taken by the Asset Performance team impacts - supply, operations, blending, and almost all other business functions, and eventually translates to the end customer whose demands drive the market. Leveraging asset efficiency and failure information to adjust supply positions puts them in a market advantage. Thus, we believe the industry should move toward the new paradigm with the combined power of business collaboration to prescribe the relationship between the failure time and operating range to get the highest value. Asset Performance today should be more than just a technology play to predict or prevent the failure of a set of equipment. To realize differentiated value in this highly competitive environment, we need to consider moving toward a unified strategy that connects multiple people, functional processes, and technology to work together. We are seeing the industry trying to drive transformational value leveraging asset performance when they can transform / rely using simplified, collaborative processes built to leverage the power of industrial internet. Let us consider an example of a pump that is continuously monitored. There is a small change in the operating metrics of the pump. The PM detects it and provides an option to repair the piece of equipment with an estimated success outcome of 80%, while an upgraded replacement of the equipment will give a successful outcome of 95%. Now, the maintenance staff can weigh the cost and success outcomes to make the most cost-effective decision. Predicting alone doesn’t seem sufficient if we are not aligned with the market demand and shipment plans. With increased digitization of the assets, it would be eventful if we could merge these actionable recommendations with the market by connecting data and trigger points across the system. The asset performance, maintenance improvements, market demands can all be connected to improve the core operation resulting in significant financial results.