Maintenance 4.0 for SMEs

Can SME plants catch up on implementation?

Maintenance 4.0 isn't a future nice-to-have, it's a practical, present day tool for meeting production goals while improving employee safety. While SMEs are rightfully cautious about investing in new technologies, the near-immediate ROI of Maintenance 4.0 technologies should not be ignored.

Even before the Covid-19 pandemic, Small and Medium Enterprise (SME) Manufacturers lagged in the deployment of Maintenance 4.0. It is tempting for SMEs who are in triage mode to focus on short-term goals to maintain economic viability. This article explores an alternative perspective: the agile adoption of Maintenance 4.0 to support operational and financial resilience during and beyond this difficult period.

What is Maintenance 4.0?

In 2013, the concept of a fourth industrial revolution or “Industrie 4.0” was presented at the Hanover Messe conference in Germany. Now more widely known as Industry 4.0, it is based on the application of technology, big data and the Industrial Internet of Things (IIoT) to transfer information and automate manufacturing processes.

In 2019, the management team of SKF Enlight AI authored the Maintenance 4.0 Implementation Handbook, which applied the concepts of Industry 4.0 to plant maintenance. It contains a framework to move from a Reactive to Predictive Maintenance model by identifying evolving machine failures before occurrence, and applying Big Data and technology innovations to increase production uptime.

Why SME’s have lagged in Maintenance 4.0 adoption

A 2019 whitepaper released by the World Economic Forum states that SMEs are “left behind” in their adoption of IIoT. Published reports and our own experience with customers point to the following constraints:

  • Management priority: In general, senior leadership at larger industrial plants have faced shareholder pressure to adopt Industry 4.0 and Maintenance 4.0 practices. As a result, we have seen the emerging role of the Chief Digitalization Officer and large-scale infrastructure investments. SMEs have not demonstrated the same level of management commitment that is a necessary catalyst for change.
  • Organizational capabilities: Maintenance 4.0 requires skills that are difficult to find, especially given the relative lack of resources of SME’s relative to larger manufacturers. For instance, in the case of Machine Learning that enables Artificial Intelligence-driven Predictive Maintenance, even larger industrial plants have struggled to recruit data scientists.
  • Technology expertise: In the last few years, the much-hyped digitalization category has been a magnet for Venture Capital investments, which has resulted in a proliferation of new technologies. SME’s have struggled to keep up with rapid pace of innovation in Operational Technology and Information Technology.
  • Ecosystem support: Inadequate vendor support to implement projects based on IIoT related technologies. Whereas larger manufacturers can rely on the expertise of third-party consultants to accelerate Proof of Concept pilots, SME’s tend to lack access to these external resources.

A Re-evaluation of the SMEs relative advantages

The common thread to these four factors is the perception that SME’s are inherently disadvantaged given their relative size and financial resources. However, we argue an alternative: SME’s are often better positioned to adjust than is widely recognized.

As a starting point, we should re-examine the accepted orthodoxy that large manufacturers are better positioned.

Let’s consider some of the challenges that large manufacturers face with Maintenance 4.0 adoption:

  • A tendency to emphasize technology as more of an end-goal than as an enabler, and consequently we often see larger plants embark on ambitious technological projects. As one industry analyst observed, the excitement is “more around the digital technology rather than the transformation itself.”
  • Many larger organizations are constrained by legacy processes and systems. Furthermore, there is often disconnects in decision making where organizational and information siloes prevent the ability to scale an initiative broadly. This is particularly the case where strategic and procurement decisions are made centrally, and implementation is driven at a plant level.

Although these phenomena can be applied to manufacturers of all sizes, they tend to be more dominant in larger manufacturing plants.

It is not that smaller plants are innately more adaptive based on size alone. However, without constraints of larger manufacturers, they can adopt a more agile approach to Maintenance 4.0. Agile does not mean the “Agile” project management methodology, per se, but rather an approach to adoption that is flexible and opportunistic.

The elephant in the room: Maintenance 4.0 is a “nice to have”

It is understandable that plants that are operating under increasingly stressful conditions may legitimately defer strategic decisions for a later date. We certainly understand the importance of the bottom line during these difficult times.

The Achilles heel of the maintenance and reliability discipline is no less relevant today: unscheduled asset downtime. The risk of reactive maintenance is particularly acute when many factories are operating with reduced manpower and spare parts may not be readily available. Identifying asset failure before forced production stoppage is more critical than ever.

A second issue of equal or greater importance is the safety of employees. Plants that may be under-staffed need to prioritize the wellbeing of frontline plant employees.

Based on these considerations, it may be tempting to the argue that Maintenance 4.0 is now a “nice to have.” However, this logic misses the point. With smart planning, Maintenance 4.0 can be used to support immediate production and maintenance goals while safeguarding employee health and safety.

A practical approach to Maintenance 4.0 for SME’s

Assessing Maintenance 4.0 within the context of enhanced employee safety and reduced reactive maintenance helps prioritize implementation areas:

Plug-and-Play asset health checks regardless of IIoT maturity level: In the ideal world, Artificial Intelligence can be applied to the data generated from the hundreds or thousands of sensors embedded in manufacturing plants. Advanced algorithms identify anomalous data patterns and provide alerts of evolving asset failure.

While Machine Learning based Predictive Maintenance is not within the reach of many SME’s, Condition Monitoring based on a Plug-and-Play model is technically feasible. Sensors can be installed to collect vibration and temperature machine data, which is transmitted wirelessly via a mobile app for instant machine diagnostics.

As a recent report from McKinsey states: “IIoT, implemented in a plug-and-play mode, can be instrumental in ensuring business continuity and minimizing economic damage by ensuring employee safety and security, improving liquidity, and lowering short-term costs.”

Remote asset monitoring: The new normal is to limit the number of frontline employees performing tasks that be done remotely. A plethora of technologies based on cloud computing and wireless connectivity allows for machine assets to be monitored in remote diagnostic centers.

Machine experts do not need to be physically present in a production plant to support local technicians. Remote expertise on root cause analysis and prescriptive guidance on performance optimization can be performed from anywhere in the world.

Drones for inspection: Many of the dangerous and labor-intensive inspection activities can be performed by drones that can reach locations that are dangerous or difficult to access. Using drones and robots for these maintenance tasks is relatively easy to implement and should be explored when considering ways to improve employee health and safety.

Summary and conclusion

The Covid-19 pandemic has forced manufacturers of all sizes to challenge existing models and ways of doing business. Given the need for creative solutions to new constraints, now is the time to tap into the practical applications of Maintenance 4.0.

Barrie Rodgers is the Product Line Manager of Mobile Solutions, and Javier Murcia is the Global Manager of REP Connected Devices.

SKF Enlight AI

Industrial plants generate terabytes of process data. SKF Enlight AI is a SaaS Predictive Maintenance solution that uses Automated Machine Learning to identify emerging asset failure patterns within this data. It provides early warnings and sensor-level intelligence to help avert unplanned downtime and meet production goals. For more information on how SKF Enlight AI can improve performance and reliability, click here.

Leave a Reply

Your email address will not be published.