Stacey Jones, Global APM Portfolio Leader, ABB Energy Industries, takes readers through the evolution of asset performance management (APM), from run-to-failure to today’s quantitative risk analysis solutions – and explains why industry cannot afford to ignore APM 4.0.
Over the past two decades, asset performance management (APM) has evolved from a condition-based monitoring role – whereby largely manual vibration monitoring may be carried out just once a month during regular operating rounds – into something more advanced, driven by industry 4.0 innovations like artificial intelligence (AI), the industrial internet of things and predictive analytics.
The current industry standard for small-to-medium-sized rotating equipment is little to no condition monitoring. What little information is gathered may be discarded once the values are deemed to be within ‘normal’ range[1]. In doing so, industrial operators are throwing away their most precious asset, data, which instead can be used to optimise production, reduce downtime, and drive profitability.
At a recent industry conference, ABB conducted a makeshift poll. First, we asked the attendees: how many of you employ some sort of condition monitoring solution? To our relief, everyone raised their hands. Then we said, OK then, how many of you use some sort of AI or machine learning (ML)-type models to help you expand that programme? The hands dropped from around 30 down to three.
Thankfully, capital expenditure (CAPEX) is no longer a barrier. With the recent decrease in the cost of wireless technology utilising connection protocols such as Bluetooth or WirelessHart, adding the ability to continuously monitor plant assets is now a cost-effective alternative to manual, infrequent condition monitoring[2].
With data-driven APM – or ‘APM 4.0’ – for all asset types, integrating remote and wireless condition monitoring on the Edge into the existing OT landscape is seamless. Once connected, the data can be analysed, with outputs/alarms accessible via email or common dashboards on-prem or in the cloud[3].
Assessing the health of crucial assets using APM
So, what is the goal of APM? The short answer is to help customers predict process failures in real time, thus improving the reliability, availability, and maintainability of their critical equipment, and enabling them to hit production, safety, and sustainability KPIs with a higher degree of confidence[4].
At ABB, we achieve this by using quantitative risk analysis and the current state of machine health to prioritise maintenance and minimise unplanned downtime and safety incidents. It wasn’t always this way. A few decades ago, everything was run-to-failure reactive, meaning equipment had to be shut down at short notice for unplanned maintenance, which is much more expensive.
The next step up was usage or time-based maintenance, where a schedule was used to assess when equipment was about to fail so it can be fixed before that happens. However, this treated every asset as having the same importance. That’s when we took the major step forward into risk-based maintenance, using failure modes and effects analysis (FMEA) and reliability-centred maintenance (RCM) to prioritise critical assets. However, this too had its drawbacks, in that maintenance is based on how an asset has broken down in the past – which still failed to use real-time data to prevent assets from failing across the board. In reality 82% of asset failures happen at random intervals[5].
Let’s use the analogy of an annual physical exam. If the physician only asks you how you are feeling as opposed to taking your temperature and blood pressure and doing your blood work, then that is only half the picture. It stands to reason that if you can get more quantitative information, you can make better decisions. In an industrial context, maintaining assets efficiently (i.e. only when needed) has been shown to decrease maintenance costs by 20–30%, and machine downtime by 20–50%[6].
Enel embraces predictive maintenance with ABB Ability™ Genix
ABB Ability™ Genix APM is being used to improve efficiency and reliability while optimising asset performance and lowering costs at 23 Enel hydropower plants across Italy, part of the green energy company’s global reorganisation of maintenance processes to boost sustainability and lower costs[7].
The PreSAGHO project demonstrates ABB’s ongoing efforts to bring together electrical, rotating, instrumentation, IT equipment and process/static equipment together in a single, harmonised APM solution for the process automation industry, one that enables predictive maintenance strategies – from condition monitoring to AI/ML predictions with combined and contextualised OT/ET/IT data.
This Software as a Service (SaaS) solution combines engineering and data science to compare fleet, plant, equipment performance versus expected performance, including indications of potential failures, and associated probability and predicted time to failure across more than 680 assets. To date ABB Ability Genix APM has been able to identify eight major faults.
Genix also offers flexible, scalable deployment across plant areas and from the Edge to the whole enterprise including integration with Enel’s CMMS (computerized maintenance management system).
With the PreSAGHO project, ABB helped Enel make the switch from hours-based to predictive and condition-based maintenance – and the benefits are clear to see. A key goal was to optimise the performance, reliability, and efficiency of Enel’s hydro fleet in order that it remain competitive with fossil fuels: by generating hydro-specific performance efficiency KPIs. ABB estimates that predictive analytics increased generation capability by 10% across Enel’s operations, and maintenance savings by up to 2%.
The transformative power of APM 4.0
In conclusion, by leveraging advanced analytics and predictive algorithms, data driven APM can empower customers to take control of maintenance, rather than let potential failures control them, and to establish a reliability culture by providing insights into asset health, identify potential issues or failures, and even recommend proactive measures that avert costly, unplanned downtime[8].
The purpose of APM is to ensure that industrial assets operate at their optimum performance and productivity levels while minimizing operational risks and maintenance costs. By managing asset performance effectively, process industry operators can improve equipment effectiveness, boost production output and energy efficiency, extend asset life, and enhance safety and sustainability standards[9] – ensuring they compete from a position of strength in today’s global marketplace.
[1] ‘ABB brings Advanced Analytics and Enhanced Asset Performance into Reach’ – ABB white paper https://campaign-pa.abb.com/l/961062/2023-10-04/4ng9j
[2] ABB brings Advanced Analytics and Enhanced Asset Performance into Reach’ – ABB white paper https://campaign-pa.abb.com/l/961062/2023-10-04/4ng9j
[3] ‘ABB brings Advanced Analytics and Enhanced Asset Performance into Reach’ – ABB white paper https://campaign-pa.abb.com/l/961062/2023-10-04/4ng9j
[4] How to optimise energy consumption using APM 4.0 | ABB
[5] What is Asset Performance Management (APM)? | ARC Advisory Group (arcweb.com)
[6] Future of maintenance for distributed fixed assets | McKinsey
[7] ABB’s digital technology facilitates predictive maintenance for Enel Green Power
