Project 3

Predictive maintenance offers great potential value to the energy and water supply industry (cf. SDG7). Timely detection of required maintenance of machines, sensors, or other critical infrastructure can prevent disruptions of service and costly loss of resources.

For instance, visual sensors can be used to analyze and detect subtle patterns (Hendrix et al. 2021; van Lieshout, van Oeveren, van Emmerik, & Postma, 2020; Noord and Postma, 2017) and auditory sensors can pick up subtle changes in sounds (Buisman & Postma, 2012). More generally, artificial intelligence offers improved prediction performance on predictive maintenance tasks. Recent advances in visual object recognition and auditory analysis allow for a continuous and reliable monitoring of system states. In particular, the focus will be on self-supervised and unsupervised learning (see e.g. Olier et al., 2018). In the absence of supervisory labels, adequate priors will be acquired using large unlabeled datasets (see e.g. Ding et al., 2022). In the context of Industry 4.0, predictive maintenance leads to numerous innovations. One of the main challenges is to deal with real time-based predictive maintenance (Zonta et al., 2020). Instead of treating predictive maintenance as a simple alert monitoring, real time-based predictive maintenance offers an estimate of time-to-failure.

PhD promoters: Dr. Sebastian Olier and Prof. Dr. E.O. Postma