More Reliability Data Doesn’t Help If Plants Can’t Act on It

Predictive monitoring is supposed to reduce firefighting. But one member described an earlier vibration-monitoring effort that surfaced more problems than the plant had the maturity and capacity to consistently address.

The Skylab space station, with its solar panels and a gold sunshade, floats above clouds and blue ocean.

About this photo Skylab’s sensors showed the problem within hours. Fixing it took a plan. The station lost its heat shield on the way up in May 1973, and the workshop heated far past safe limits. Engineers had about ten days to build a fix the first crew could carry up: a parasol-like sunshade, pushed out through a small airlock. The temperature came down.

Source: Skylab Orbital Workshop seen from the Skylab 4 command and service modules, Skylab 4 crew, February 8, 1974. NASA, SL4-143-4706 (GPN-2000-001055).

The Story in Brief

“Predictive technology only creates value when the operating system around it is ready to respond. Clean asset information, useful PMs, prioritization, clear ownership, and the capacity to act on signals matter as much as the monitoring technology itself.”
Andi Del Collins Executive Director, Manufacturing Board

Picking Up the Story

The Constraint Is Not Always the Technology

Predictive monitoring is supposed to reduce firefighting. But one member described an earlier vibration-monitoring effort that surfaced more problems than the plant had the maturity and capacity to consistently address. More information did not automatically create better reliability; without the routines and resources to respond, it created more signals competing for attention.

That experience captured the tension running through the discussion. Manufacturers increasingly have tools that can detect equipment problems earlier. The harder question is what happens next: who monitors the data, which signals matter, who owns the response, and how the organization makes sure proactive findings become action rather than another layer of work.

“The central team needs to feel like they own the result as much as the site team.”

Focus of the Discussion

The Hard Part Is Turning Signals Into Action

One member described the challenge as separating the day-to-day work required to “run and maintain” a plant from the work required to improve its reliability system. Plant teams will always face urgent production and maintenance demands, making it difficult to consistently protect monitoring, analysis, and optimization work from the daily firefight.

Some manufacturers are addressing that capacity problem through more centralized monitoring. Dedicated teams can watch equipment across sites, interpret signals, and help prioritize what requires action. But centralization does not solve the problem if those teams simply identify an issue and pass it back to an already stretched plant.

The stronger model keeps ownership with the problem through closure. And because neither monitoring nor response capacity is unlimited, members are concentrating predictive investment where earlier intervention materially changes the outcome. One organization reported payback of less than nine months on some critical assets, but diminishing returns as coverage extended to less-consequential equipment.

Key Takeaways

  1. Assess operating readiness before adding more predictive technology. Clean asset information, useful PMs, functioning maintenance routines, prioritization, and response capacity determine whether another signal will prevent failure, or simply add another alarm. Member experiences show that foundational reliability work can be the higher-priority investment.

  2. Separate reliability improvement from the daily firefight where scale supports it. Centralized monitoring can protect analytical and optimization work from plant-level “run and maintain” demands. Some members are moving in this direction, while still keeping site teams involved when local action is required.

  3. Assign ownership through closure, not just detection. A monitoring team that identifies a problem without helping drive the response can leave proactive findings competing unsuccessfully with urgent site work. Define who owns the result, how issues are prioritized, and who remains responsible until the action is complete.

  4. Concentrate predictive investment where avoided failure has meaningful economic value. One team reported payback of less than nine months in some critical-asset applications, but diminishing returns as monitoring moved beyond its most consequential equipment. Use asset criticality and avoided downtime to determine how far predictive monitoring should extend.

About the Manufacturing Board and Assemble

The Manufacturing Board is an Assemble community that helps senior manufacturing leaders at the world's largest organizations make better, faster decisions through trusted peer conversations.

We selectively share highlights from confidential member discussions to help leaders understand how peers are approaching complex operational challenges and emerging industry trends.

If you'd like to learn more about the conversations happening inside our peer network, or how members connect with trusted peers to solve critical challenges, please contact us.

About the author

Jay Avery

Contributing Editor Jay Avery is a freelance journalist and writer whose work has appeared in The New York Times, Vanity Fair, and Architectural Digest. She began her career in marketing and content roles at Uber during its early startup years and later at RideAustin, bringing a strong foundation in both storytelling and strategic communications. Jay holds a law degree from the University of North Carolina and is based in Raleigh, North Carolina.