Brian McCormick is EnerMech’s CSVP Lifting solutions. He leads a global team with a focus on growing the business, driving innovation, and delivering market-leading solutions to clients. He has a particular interest in investigating how AI-driven technology could lead to advanced predictive maintenance programs, improving operational efficiency.
Reliability in cranes and lifting is crucial to ensure operational efficiency and safety, and a fit-for-purpose maintenance schedule is vital to ensure unscheduled breakdowns are kept to a minimum.
With the likelihood of unexpected failure potentially increasing as assets exceed their expected lifespan, incorporating AI-driven technology and real-time monitoring into a predictive and preventative maintenance approach has the potential to set new standards across the global cranes and lifting sector.
Historically, maintenance has either been reactive following breakdown without advance warning of failure or via fixed scheduling. From that, the sector has generally moved to a condition-based maintenance model based on knowledge of historical failure rates.
But it’s time to take things to the next level with a leap to an approach led by AI-technology that would see sensors fitted to key areas of the equipment to measure parameters based against alarm and trip levels. For example, in the energy sector, these would be connected remotely to on or offshore hubs which would send out real-time alerts when the equipment parameters start to approach alarm levels, with associated software analyzing and predicting as and when failures will occur.
This modern approach to predictive maintenance would leverage advanced diagnostics and monitoring technology to forecast potential issues. The deployment of real-time data collection from critical crane components would enable early detection of irregularities, enabling maintenance teams to intervene before minor issues became major problems while maintaining optimal crane performance.
The technology to do this already exists and is in use on some of the equipment used by the oil and gas industry. We now need to take this forward by engaging with the providers of such technologies to bring them into the cranes and lifting sector.
Integrating multiple methodologies and capitalizing on this existing technology, predicting and being able to address problems before they arise would maximize crane reliability and operational efficiency, reducing downtime and safely extending the lifespan of these critical assets.
And by following OEM maintenance recommendations and industry best practices, this new approach would ensure that every crane and lifting asset would receive a tailored maintenance plan aligned to its operating requirements and service life requirements.
EnerMech is committed to advancing industry-leading maintenance practices. It’s an approach I strongly support. Embracing and enabling a forward-looking methodology to maintenance practices that capitalize on the availability of today’s AI-driven technology to predict and prevent problems before they happen is absolutely vital.
The technological tools we need to make this happen already exist. We now need to push ahead with a collaborative, concerted approach to bring them into our toolbox.