When ICL Suria’s mine expanded production in 2025, the plant suddenly became the bottleneck. Operating 24/7 with only one planned maintenance day per month, they needed to achieve 95% plant availability. Keeping the facility operational for that amount of time was a performance level they’d never hit before. The solution wasn’t more maintenance staff or overhauled processes. It was strategic machine monitoring expansion that gave them the visibility to make confident decisions, extend equipment life safely, and turn maintenance from constraint into enabler. The result: 95% availability achieved in 2025 for the first time, plus a workforce benefit nobody saw coming. That performance earned them their second consecutive Spotlight Award—and their approach offers lessons for any facility considering expansion.
The gearbox on a critical conveyor feeding the plant was vibrating badly.
Avraham Boublil, Process Engineering and R&D Director at ICL Suria, had a decision to make. The facility processes millions of tons of sylvinite annually at Spain’s only potash production plant, running 24/7 with just one planned maintenance stop per month. Every repair decision carries enormous weight.
He had three options:
1. Stop production immediately and replace the gearbox.
2. Ignore it and hope for the best.
3. Make a strategic decision based on what the monitoring data was telling him.
“If we didn’t have this online monitoring,” Boublil reflects, “probably our decision would be different.”
They chose to lubricate the gearbox, continue monitoring it closely, order the spare part, and schedule the replacement for their planned maintenance day. The gearbox held. Production kept running. No emergency shutdown. No expedited parts. No weekend callouts.
That’s the ROI of expanded monitoring coverage—not just knowing there’s a problem, but having the confidence and lead time to handle it strategically.
When the Mine Expands But Your Maintenance Window Doesn’t
ICL’s challenge in 2025 was unprecedented. When their mine expanded production, the plant suddenly became the bottleneck. They were required to achieve 95% plant availability, keeping the facility operational and producing 95% of scheduled time, with no historical baseline for this level of performance.
The constraint was unforgiving: continuous operations with only one monthly window to complete all planned maintenance. Fix something now and halt production, or risk catastrophic failure waiting for that single maintenance day.
Most facilities would panic. Boublil’s team did the math instead.
They looked at their conveyors, pumps, and mills—equipment that could stop production but wasn’t giving them advance warning. They calculated the cost of surprise failures when scheduled downtime was so limited. They considered new monitoring capabilities like ultra-low RPM technology that made previously “unmonitorable” equipment viable.
“We just did the calculation and understood that we have more equipment that could justify the cost,” Boublil explains.
The business case was straightforward: , emergency shutdowns, and lost production hours? For a continuous operation shipping agricultural fertilizers and industrial salts globally, the answer justified expansion.
The Foundation That Made Growth Possible
Here’s what made ICL’s expansion different from facilities that add sensors and struggle: they already trusted what they had.
“When equipment shows danger, you have hours—maximum a day—before it fails,” Boublil says. “So you need to act fast. We take every alarm seriously, especially danger alerts.”
That’s rare. Many facilities struggle with monitoring systems that generate too many false positives—alerts pile up, teams stop trusting them, and the equipment becomes shelfware. ICL avoided that trap entirely.
But when your alerts are accurate, everything changes. You investigate immediately instead of waiting to “see if it’s real.” You make confident decisions about lubrication and scheduling. You order parts in advance instead of emergency expediting.
ICL had built that trust with their initial monitoring deployment. The accuracy gave them no choice but to act. When the system said “danger,” they’d learned it meant they had hours to a day before failure. That urgency, combined with proven accuracy, created the foundation for confident expansion.
Scaling Without Drowning
ICL avoided the trap that kills most coverage expansions: overwhelming the team with alerts they can’t handle.
They built something simple: plant-wide WhatsApp groups where every alert triggers immediate discussion. The condition monitoring or availability engineer typically responds first, but everyone can see what’s happening and why. No notification goes unexamined.
“Each equipment type has unique issues,” Boublil notes, “but lucky for us, Augury covers all.”
This matters because more monitored equipment means more alerts. Without clear ownership and process, teams get buried. One person becomes the bottleneck. Alerts get ignored. The program stalls.
ICL made alert response a team activity from the start. The process scaled as coverage grew because everyone knew their role. When you operate 24/7 with one maintenance day per month, efficiency isn’t optional.
Autumn 2025: The Breakthrough
For the first time all year, the plant was operational and able to produce 95% of its scheduled time.
This wasn’t just hitting a number. It was a new operational capability. All three of ICL’s main KPIs connect to their monitoring program: recovery, operational time, and tons per hour. Without visibility across all critical assets, they couldn’t maintain the throughput their expanded mine operation demanded.
The plant went from being a constraint to being an enabler. When the mine increased volumes, the plant kept pace. Maintenance decisions that used to force production delays now happen during planned windows. Equipment that used to fail unexpectedly now gets serviced proactively.
“We still have a long way to go in our maintenance process,” Boublil says, “and of course, Augury has a very big part in this run.”
That mindset—treating monitoring as a continuously improving capability, not a finished project—is exactly what separates facilities that get ongoing value from those that plateau.
The Benefit Nobody Expected
Two months before ICL hit their 95% availability target, they hired a new reliability engineer.
He gets notifications about equipment he hasn’t even located yet. The alerts force investigation. Investigation builds knowledge. Knowledge accelerates competence.
The system forces learning in real time. “For him, it’s priceless,” Boublil says. The new engineer discovers critical equipment issues he would never have known to look for.
Instead of spending years walking the plant to understand which equipment matters most, he learns through live problems—investigating alerts, understanding failure modes, building judgment through actual decision-making rather than shadowing.
One engineer can respond to alerts across dozens of assets. Knowledge gets captured in the system instead of staying in individual heads. When you operate 24/7 with one maintenance day per month, this kind of efficiency matters.
What Made It Work
ICL’s expansion succeeded because they built trust first. When alerts are accurate and teams act on them, expansion becomes the obvious next step, not a risky experiment. Their plant-wide communication kept it manageable, so the same team could handle more equipment as coverage scaled.
They also treated monitoring as an evolving capability, not a one-time installation. “We feel like partners, not just customers,” Boublil says. “The service is so good that we’re always open to trying new things.”
That mindset—trust the alerts, scale the process, keep improving—is why ICL achieved 95% plant availability for the first time. And why they’re not done yet. What could a similar approach unlock for your facility?
See how leading manufacturers expand monitoring coverage strategically:
Explore case studies and Spotlight Awards winners to discover the best practices for scaling condition monitoring programs while growing production output.
