Only at Scheduled On-Condition Tasks

The falling cost of sensors for Industrial Equipment & the popularity of AI-based solutions means that Organizational teams are defaulting to using this strategy on all their Equipment, regardless of its criticality or other effectiveness. This is a strategic error.

As any Maintenance & Reliability practitioner would know, there are many types of Maintenance Strategies: Reactive, Preventive(PM), Condition-based(CBM), or Predictive (PdM). If none of the maintenance strategies mitigate the risk of failure then a re-design is necessary. Each asset operating in its application context would require a specific type of strategy to maximize Availability, reduce failure Risk, and Cost. The decision-making process to choose the appropriate strategy is given in the most cited literature in the maintenance community: Reliability-centered Maintenance (RCM). According to this report, the decision tree looks likes below and the user answers the question in sequence to determine the correct strategy. While this is a time-consuming process to evaluate each asset, RCM Analysis is necessary and pays dividends generously during operations.

So, where does the latest tool, IoT Sensor & Analytics, fit into the RCM Decision tree?
It fits at the Scheduled On-Condition task step!

It works only at this step because the asset’s criticality requires to have a low failure risk and the feasibility of monitoring the asset continuously to detect a failure is effective. At all other conditions, the asset might not be expensive enough to monitor or critical enough to spend resources, or hazardous enough to keep inspecting often. You can safely avoid installing the fancy new IoT sensors on these assets and focus on the critical few. Narrowing the focus of the IoT-driven Predictive Maintenance (PdM) will increase its effectiveness, generating more ROI for your investment.

As I say often at Owtrun: IoT Infrastructure, Analytics, and ML Algorithms are just tools in the Reliability toolkit. Not all tools will fit at all locations and not one tool will solve all problems. Choose them & Use them wisely.

If you’d like to know how to analyze assets, implement ML-based Predictive Maintenance, or develop a strategy for your organization, I can help you. Check out www.owtrun.com for more.