Today, predictive maintenance is a necessity for companies in many fields. Preventing breakdowns and malfunctions, or carrying out equipment overhauls and replacements at the right time, can help avoid the significant financial repercussions of a machine or electronic process shutdown, or the premature replacement of a still-functioning device, for example.
Predictive maintenance relies on data analysis to intervene at the right time. In this context, artificial intelligence could prove to be a key element. But how do you set up a system for the automatic collection of relevant data? And once acquired, how to manage this data to consolidate predictive maintenance?
Join us on September 28 for a discussion between peers and academic institutions on this topic.
As part of the event, a talk will be given by Prof. Dr. Jean Hennebert on the remaining research challenges in this field.