PreMa4MM – Predictive Maintenance for Mobile Machines

Modern mobile machines already contain a wealth of valuable information. Through CANbus networks, data is collected on operation, load, performance, usage and possible anomalies.

However, the challenge is not only to collect this data, but above all to interpret it reliably. Which signals indicate wear? Which patterns may predict a failure? And how can these insights be translated into concrete maintenance actions?

PreMa4MM aims to help companies take that step: from raw machine data to useful insights for maintenance, fleet management and asset management.

• The project will examine, among other things:
• realtime data collection from mobile machines;
• the reading and centralisation of J1939-CANbus data;
• the application of probabilistic machine learning;
• technological validation through practical cases;
• economic validation of predictive maintenance;
• the development of practical guidelines and usable tools for companies.

According to the project description, PreMa4MM will also investigate which commercial solutions are currently available for realtime reading of standardised CANbus data, which data pipelines are needed for predictive maintenance, and how the economic added value of broader application can be validated.

PreMa4MM aims to demonstrate how companies can use data from mobile machines to better predict maintenance needs and reduce downtime.

The project results should provide companies with practical insights, guidelines and tools that help them apply predictive maintenance more concretely in their own fleet management and maintenance strategy.

More specifically, the project aims to contribute to:

• better insight into the technical condition of mobile machines;
• early detection of wear and potential failures;
• less unplanned downtime;
• more efficient maintenance of large machine fleets;
• better-informed maintenance decisions;
• a clearer business case for predictive maintenance.

The project results will be bundled and translated into practical tools that can help companies optimise the day-to-day monitoring of their machine fleet.

The project is aimed at organisations across the full value chain of mobile machines and data-driven maintenance.

This includes, among others:

• companies with their own mobile machines;
• construction and infrastructure companies;
• logistics and port companies;
• machine rental companies;
• service and maintenance companies;
• machine builders;
• suppliers of sensors, hardware and software;
• technology providers and integrators;

companies active in data analysis, AI or predictive maintenance.

The Flemish Council of Universities of Applied Sciences and Arts describes the target group broadly: any company involved in the data, machines or reliability of non-road mobile equipment can play a role in this project.

BEMAS supports PreMa4MM through its network in maintenance, reliability and asset management.

As with other innovation projects, BEMAS uses its communication channels and community to make project results visible, inform companies and connect relevant organisations with the project partners. In projects such as SM4RTENANCE, BEMAS also plays an important role in communication, dissemination and linking project results to the maintenance and asset management community.

For BEMAS, PreMa4MM fits closely with a broader evolution in maintenance and asset management. Predictive maintenance has been an important topic for some time, but its application to mobile machines remains complex for many organisations.

Mobile machines often operate in changing conditions, data is not always easy to access and the business case must be clear. That is precisely why a practice-oriented research project such as PreMa4MM is valuable for companies that want to organise maintenance in a smarter, more reliable and economically better-founded way.

For the further development of the project, PreMa4MM is looking for additional companies willing to participate in the advisory committee.

Participating companies can contribute practical cases, share operational challenges and test the project results against their own reality. This ensures that the project remains closely connected to the needs of the sector.

Participation is particularly relevant for companies that:

• want to explore how they can make better use of data from mobile machines;
• want to strengthen their maintenance strategy with predictive maintenance;
• want to gain insight into the economic added value of data-driven maintenance;
• want to learn from practical cases and technological validation;
• want to help shape useful tools and guidelines for the sector.

After the project, participating organisations will be able to translate the results more quickly into their own operations and machine fleet.

Companies that would like to contribute to PreMa4MM or receive more information about participation in the advisory committee can contact:

Kris Martens
Research Coordinator Sustainable Energy & Mobility
Karel de Grote University of Applied Sciences and Arts
kris.martens@kdg.be
+32 474 91 79 05

You can also signal your interest through BEMAS. We will be happy to put you in contact with the project partners.