The aim of this special session is to bring together academic and industrial leaders who will present recent challenges, developments and achievements in the field of evolving and adaptive intelligent systems for condition monitoring and predictive maintenance in Industry 4.0 scenarios to a broader audience and readership. The peculiarity of this special session is on its diffused focus that lies not only on the (adaptive, incremental) learning aspects but also on monitoring, control, and optimization aspects, embracing also technological-oriented challenges and solutions. So far, predictive maintenance has been only marginally addressed in the literature. The reasons are the most disparate, while the scarcity of training data and of collected instances about faulty events (rare by definition) are currently the most relevant ones. Control aims at ensuring that systems execute specified or desired behavior to perform specific tasks for which they were designed. Because of several external perturbations as uncertainty, erroneous or incomplete measurements, unpredicted faults or the emergence of new operation modes, control and monitoring strategies require to be adapted over time in order to keep the system executing desired or safe behavior and protecting it from unforeseen or dangerous behavior, as well as to predict possible malfunctioning that will require maintenance activities. Within this special session, we expect to see works showing decision support tools and recent progress in condition-based monitoring and predictive maintenance. These include embedding early anomaly/fault detection, diagnosis and reasoning, remaining useful life prediction (fault prognostics), quality prediction and self-reaction, as well as optimization, control, and self- healing techniques. The application of the techniques is expected in various types of industrial (production/utilities/equipment/plants/smart devices, etc.) systems addressing several challenges in Industry 4.0 and different tasks dealing with Big Data Streams, Fog/Edge computing paradigms and the Industrial Internet of Things.

Massimo Vecchio, eCampus University, Italy

Marco Roveri, University of Trento, Italy