Early in Matthew McLaughlin’s tenure as reliability engineer at Domtar, an engine at the paper mill in Kingsport, Tennessee, failed.
McLaughlin said his manager asked him to review the entire day’s sensor data collected by 450 sensors and recommend a fix for the engine, but he knew that was an impossible task.
“It would take me 32 weeks to analyze all the data we collected in one day,” McLaughlin, who joined the company in 2024, told Business Insider.
If production companies As they adopt promising new AI technologies, they often face the challenge of learning to do things differently, such as implementing new tools and processes to get the most out of their technology investments.
In the years leading up to McLaughlin’s arrival, Domtar implemented this AI-enabled sensors from Waites Sensor Technologies to continuously monitor equipment vibrations – which signal the health of a machine – and provide that data to prevent malfunctions.
Armed with more data than before, Domtar needed a new way to do that manage it all so that it could optimally utilize the capabilities of the Waites sensors.
That’s where reliability engineers like McLaughlin come in: they’re tasked with improving a company’s technology and digital resources through data analytics, risk management, technical expertise and communication skills. As AI systems become increasingly integrated into workflows, reliability engineers like McLaughlin must develop new methods that bring people and technology together.
“This was the line-in-the-sand moment where we had to do something different,” McLaughlin said. He added: “It cannot be treated as a legacy predictive maintenance program; It needed to be treated like the advanced system that it is.”
Zoom in on the data about weekly partner conversations
To move away from manual analysis and make better use of Waites’ machine learning technology, McLaughlin said he decided to rely on the technology company for more detailed and consistent support.
Domtar already had access to Waites’ full service offering, including a Waites analyst who could learn about Domtar’s facilities, pain points, personnel and staffing levels to help the company tailor the AI recommendations from its sensors.
McLaughlin said he started using this extra support by attending monthly calls with the sensor company. During one of those calls, the Domtar team said the factory was underutilizing tools that could provide additional data and potential value, and the calls were repeated weekly. Domtar started sharing their data thermal imaging camerainfrared camera and ultrasonic meter with Waites.
McLaughlin said: “Let’s give as much feedback as we can because with machine learningIf you don’t teach him anything, he won’t learn anything.” Within three months of this more active approach at Waites, McLaughlin said, Domtar began to notice significant improvements.
The convergence of data and human expertise
AI performs the primary analysis, but relies on the Waites analyst, on-site vibration analysis experts and Domtar maintenance staff to diagnose the problems, says Rob Ratterman, Waites CEO and co-founder.
“It’s not just a change in technology. It’s not something you just plug in,” Ratterman told Business Insider. He added: “You can plug in our system or any other sensor system and you’ll get some benefit, but to get the kind of results Matt is seeing requires someone to become a lighthouse that can monitor the entire company,” Ratterman told Business Insider.
Shift supervisors, production superintendents, high-level managers and the general manager can access the Waites system to stay informed of alerts and solutions. McLaughlin’s team tracks every network and equipment action item, including response time, and ensures that action items are less than 30 days old.
The analytical AI stocks are helping them fine-tune maintenanceincluding the viscosity class of the lubricant. With a lower viscosity, they can use less horsepower and draw fewer amps on the motors, which reduces costs, says McLaughlin, who is now a reliability inspector with the company.
Domtar declined to reveal its AI costs to Business Insider, but McLaughlin said the system is worth every penny. “We justify the cost – which is very reasonable compared to other options – of the Waites system because we saved 1,546.65 hours of unplanned downtime,” he estimated.
Earn employee trust through daily reporting and tracking
McLaughlin also began sending daily email summaries about the system and alerts to Domtar’s longtime employees.
Operations managers called him whenever they received an alert to ask how the reliability team handled it, he said.
“Then those calls stopped. Yesterday I spoke to a paper machine supervisor who said he doesn’t look at the warnings anymore,” McLaughlin said. He also said that trust has grown so high that Domtar “bases multimillion-dollar decisions on our Waites data, and it has become an integral part of our planning process.”
Domtar now uses 748 sensors that monitor its staff, McLaughlin said. The Waites sensors continuously detect machine vibrations that signal problems (such as a crack in an engine bearing, misaligned engines or lack of lubrication) to predict impending component or machine failure or to flag potential problems six months later. This allows companies like Domtar to order specialized parts and keep their machines running, Ratterman said.
The sensors allow Domtar to make small, consistent improvements and prevent component failures. For example, a drive belt supplier recently told McLaughlin that its Domtar facility has not purchased fan belts in a year, which McLaughlin attributes to the regular monitoring and maintenance the sensors support.
“We couldn’t do that without AI-driven computing power,” he said.
