New project on maintenance prediction for industries
With the use of big data, Leiden University is aiming to develop a system that sends automatic alerts when certain Industrial parts are starting to wear out. Researchers of the the Leiden Institute of Advanced Computer Science (LIACS) are developing a predictive maintenance platform together with, among others, KLM, Honda and CWI. The LIACS researchers’ optimization algorithms make it possible to reschedule maintenance events dynamically for cross-industry users.
Too early or too late
Every enterprise has to deal with it: maintenance of machinery and infrastructure. Traditional maintenance concepts rely on a ‘fixed interval approach’, which takes into account a significant safety margin. As a consequence, maintenance is almost always taking place too early or, in worse cases, too late. This makes it probably one of the most inefficient, and at the same time most critical, activities in industry.
Predictive maintenance
The appropriate infrastructure for big data collection, preprocessing, and analytics will open the door to predictive maintenance: optimize the best moment to perform maintenance with respect to costs and safety. Predictive maintenance allows companies to schedule at their own convenience and thereby preventing unexpected failures. The CIMPLO approach will drive down costs immediately, while preserving proper safety levels and human capital deployment.
Read more about the CIMPLO research project.