Leveraging AI: Aertssen reduces machine downtime with predictive maintenance

The essence

Our partnership with Aertssen, a leader in construction, shows how you can leverage existing data for AI integration into the heavy industry sector. By developing a Proof of Concept (POC), we helped transform the way maintenance is conducted on heavy machinery, like caterpillar cranes, and making it more efficient and predictive.

The challenge

Reducing machine downtime with predictive maintenance

Aertssen operates an extensive fleet of heavy equipment, crucial for its wide array of services. The maintenance of this equipment poses a substantial challenge; unplanned downtime not only disrupts project timelines but also incurs significant costs. Traditionally, maintenance schedules were largely reactive or based on predetermined intervals, which could not account for the actual condition or usage of the equipment, leading to either premature or delayed maintenance actions.

The Solution

Addressing this challenge, we designed a proof of concept (POC) that employs predictive analysis to anticipate maintenance needs. Utilizing Aertssen’s historical data on maintenance and machine breakdowns, the tool applies AI algorithms to accurately predict when machinery is likely to require maintenance. This predictive approach aims to anticipate equipment failures, ensuring that maintenance is performed just in time to prevent downtime.

Our POC includes a visualization tool, which uses color coding to indicate the maintenance status of each machine, ranging from green (operational) to red (urgent maintenance required). Using filters like type or brand of machine, you can see all relevant information: identification number, project number, measured operating hours up till now, location, last maintenance date, number of maintenance interventions, …

This enables a quick and intuitive assessment of the fleet’s condition, facilitating the efficient allocation of maintenance resources.

The future

Looking ahead, the next phase of the project will focus on optimizing the deployment of field technicians. By leveraging the predictive maintenance schedule and the geographic location of both technicians and machinery requiring maintenance, the goal is to minimize travel time and ensure the most effective use of resources. Furthermore, we plan to enhance the system with traffic data integration, aiming to create an ideal schedule for technicians that accounts for real-time conditions, thereby streamlining operations further.

This project not only showcases the potential of AI to revolutionize maintenance strategies in the heavy industry but also sets the stage for future innovations that can significantly boost operational efficiency and reliability.

We are excited about this next step and our further partnership with Aertssen!

This project was in close collaboration with MbarQ.