Challenge
Companies maintain their machinery in different ways. This can be in a reactive, preventive or condition-based manner. In the past, much attention was also paid to predicting the remaining useful life (RUL) of a machine. For this, it was important to understand the physics of your machines to the core.
Whichever way you go about it, the goal of a good maintenance strategy remains the same: to ensure continuity and thus reduce operating costs - after all, machine/production downtime automatically means high costs. This can be achieved in 2 ways:
- In a 'down-to-earth' way using historical, operational information;
- In a cost-conscious way.
In this project, we look for a smart way of maintenance, linking human expertise, machine data and machine learning.
Here, we focus on the following sectors/applications:
- Manufacturing companies with CNC machines, overhead cranes, cranes, compressors, ... who want to save costs;
- Companies deploying a fleet of assets (e.g. charging stations, wind turbines, ... ) and responsible for maintenance;
- Suppliers of consumables such as machine tools, rotating equipment;
- Technology suppliers to support maintenance strategies.
Project goals
In this project we use readily available operational data (e.g. amount of active hours, product volume, historic maintenance interventions, quality report … ) and combine it with cost models to account for cost of too early tool replacement, risk of downtime, etc..
The goal is to define a machine learning-based tool supported by expert knowledge (and potentially more detailed condition monitoring machine data) that lowers the costs of your maintenance programme.
Would you also like to participate in this project?
COSTLEAP_IRVA is an industrial research project. We are looking for companies that want to be part of the user group and work with us to valorise the project.
Interested? Fill in the form below and we will contact you as soon as possible.
