In the past, across the process industries in particular, evolutionary improvements in maintenance have generally taken the form of finding increasingly sophisticated scheduling techniques. Yet, recent studies indicate that most equipment fails on a ‘random’ basis no matter how much assets are serviced and inspected. In other words, failures cannot necessarily be correlated to how maintenance was performed. And, as Michael Saucier from the software provider AspenTech, shows here, adoption of a technology that’s already available can remove the arbitrary nature of inspections and, in the process, make operations more predictable, more efficient and safe.
Today, organisations across a wide range of process industry sectors are waking up to the fact that it is time to abandon the calendar as the driving force behind maintenance schedules and replace it with predictive, or prescriptive, analytics. Yet, the benefits that prescriptive analytics can deliver extend well beyond the traditional process industries. One area where we are seeing the data-driven insight that the approach can bring achieve real traction today is rail transport.
Both global rail traffic in general and more specifically global freight traffic are expected to show strong growth in the coming years. According to a recent report from strategic consultancy, SCI Verkehr, all types of rail traffic are projected to grow up to 2025, building on growth already achieved since 2005. Given this growth, however, the pertinent question is: how do we ensure safety, reliable service and continued operating ratio improvements? Focusing on service and productivity improvements can help lower operating ratio, increase levels of safety and guarantee on-time performance. Revenue can be positively impacted through service efforts tied to faster turnaround, enhanced reliability, quicker transit and improved frequency. In addition, lower operating expenses can result from productivity efforts tied to train density, people efficiency, fuel optimisation and rolling stock utilisation.
These are high-level performance metrics. The most direct benefit of applying the latest prescriptive analytics technology, however, often simply comes from preventing train locomotive breakdowns. Diesel engines and locomotives endure high stress conditions that can result in failure. Yet, too many rail operators still depend on traditional run to failure operational models, which in turn means they can be plagued by serious ‘line-of-road’ locomotive failures which previously remained completely undetected using existing techniques.
Precise operating patterns
The latest prescriptive maintenance approaches can guard against this through a combination of internet of things (IoT)-based, Big Data and machine learning technology. In line with this, it is possible today to effectively deploy autonomous agents that use sensor-based technology to identify changes in equipment conditions. In a typical scenario, anomaly and failure agents can be deployed to learn precise patterns of normal operating behaviour, excursion from normal conditions and minuscule pattern changes that result in known failures.
To further extend this scenario example, if a known failure is detected the failure agent can determine when that failure will occur if the condition is not corrected and then immediately alert maintenance. As a result, a reliability engineer will receive the failure signature alert, assess the severity of the issue and make a recommendation to the maintenance department. Thereafter, a maintenance planner confirms the diagnosis and schedules requisite corrective action. If there is enough lead time before more damage occurs, the locomotive can be scheduled for service and repair at a convenient time.
This combination of IoT and machine learning can do far more than merely solve the immediate problem, however. In this situation, in addition to the corrective maintenance performed on the engine, the root cause of the problem will be documented, adding to the operational team’s overall knowledge of the issue. If the failure signature has detected the failure pattern plus any new pattern data, the agent will be updated to reflect this – and will become more intelligent as a result. At a higher level, the benefits of this approach become apparent and extend far beyond the immediate issue of preventing the breakdown of a particular engine.
Using prescriptive analytics, even a specific ‘granular’ action like analysing oil samples across an entire fleet of locomotives can bring insight that helps increase locomotive reliability and improve asset utilisation across the entire estate. Instead of simply relying on traditional threshold analysis which might leave underlying issues hidden, a more in-depth prescriptive analytics approach has the potential to drill down into specific issues around iron and viscosity soot levels, and low water pressure, for example, all of which could herald imminent problems that need to be addressed immediately.
Taking such action could in turn lead to improved maintenance planning and a more proactive preventive maintenance operations across the organisation – and bring significant cost savings. By extending out insights gained from analysis of individual or small groups of locomotives to entire fleets, there are a raft of additional benefits to be tapped into. By adopting a prescriptive analytics approach, safety levels could be increased, considerable additional savings could be achieved and operating ratio could be boosted, while potentially lowering fuel consumption and increasing train speed at the same time. Importantly, all of these are key objectives for any rail transport provider. That’s why – in a challenging and competitive sector like rail – prescriptive analytics is key and has to represent the way forward.
Michael Saucier is product manager at AspenTech.
You may also like this from SmartRail World:
From the vaults: Rail predictive maintenance; success, first steps & lessons learned.