Acheiving profitable reliability from IIoT

Finding ways to improve operational profitability is not a new topic. If you have not already started down this road, there will be opportunities wherever you look. But if you have been working on this for a few years the low hanging fruit have gone, so what about profitable reliability?

Today’s plants face managing increasing speed of business and preparing for emerging technologies. According to Schneider Electric, both play an important role in determining whether the organisation will remain competitive and relevant.

For manufacturers, the goal of both maintenance and operations is to maximise operational profitability. Approaching reliability, efficiency, and profitability from a common strategic viewpoint is essential. This collaborative approach is a form of profitable reliability.

According to ARC Advisory Group, predictive maintenance strategies can deliver twice the cost benefits of preventive strategies, and in comparison to preventive strategies, reactive maintenance could increase the lifecycle maintenance costs by a factor of 10 when a failure occurs.

Industrial maintenance tools and practices, intended to improve asset reliability, have progressed and evolved over the past two decades. We have moved from reactive maintenance through scheduled maintenance. The data needed  for predictive and prescriptive maintenance are becoming available due to IIoT and more monitoring.

Profitable reliability

Analysis of performance data gathered from the equipment on the plant floor allows operators to better assess when a piece of equipment will fail. They can then take preventative measures to either avoid the failure or to adjust the process to ensure production efficiencies.

Advanced analysis results from three layers:
– The first layer uses asset-specific algorithms, rules, and thresholds derived from many data points gathered over time across many sites. This helps gauge the performance of the assets (e.g., how long that motor will last, or whether warning signs are being detected).

-The second layer consists of a service bureau, to determine if the system has detected is a normal condition, or it requires additional investigation.

-The third layer employs a remote expert, if there is a need for more investigation. The expert analyses the data, determines the root cause, and develops a detailed event report.

Using a third-party cloud-based asset management model is a scalable option. The industrial site can start small with billing for monitoring on an ad hoc basis. For example four or five pumps or if the electrical system is being monitored, the main breakers. Expanding the systems can then progress until the site-wide optimisation of all assets.

Proactive maintenance strategies

Predictive and prescriptive (sometimes called proactive) maintenance strategies are usually aided by IIoT-driven modernisation. In both approaches, monitoring the processed data identifies trends and issues alerts prior to failure. Predictive condition monitoring is most appropriate for predicting failure in simple systems. More complex systems involve prescriptive condition monitoring to analyse multiple variables and predict failure. This requires a wider awareness of operating conditions and accurate diagnosis of pending issue.

Measuring real-time reliability risk results in real-time reliability control. This concept extends itself to traditional maintenance management. Take for example a compressor that is likely to fail within the next six hours, i.e., the risk is high. The operator, might respond by slowing the compressor rotation, extending the time before failure. This provides the maintenance team time to find a develop a response.

It is important to note that in the IIoT age, smarter, autonomous assets can sometimes control their own real-time reliability.

As business-performance managers, operators will be able to adjust the set points and see the impact they and their adjustments are having, not only on the process, but also on the profitability and reliability of the optimised assets. They can then apply this feedback to make decisions that maximise profitable reliability without significantly increasing risk.