Università degli studi dell’Aquila - UNIVAQ
The University of L’Aquila is a competitive research and teaching institution in Italy, whose foundation dates back to the Middle Age (1596). The University has seven departments and two centers of excellence (CETEMPS, DEWS) and offers a broad variety of programs in engineering and applied sciences.
The UNIVAQ/DEWS started its operations in 2001 after the Ministry of Scientific Research and University awarded grants for the formation of centers of excellence on a competitive basis. DEWS was among the very first organizations that proposed research on the use of networks of sensors, controllers and actuators to solve society scale problems such as health, disaster recovery, transportation systems, and education.
DEWS researchers are active in networked embedded systems automatic control, analog and digital electronics, computer science and telecommunications. In this context, the Centre has been able to plan and manage projects of significant complexity as well as to spin-off an engineering company. DEWS has been a member of the HYCON Network of Excellence (Hybrid control: taming heterogeneity and complexity of networked embedded systems) and HYCON2 (Highly-complex and networked control systems) Network of Excellence.
UNIVAQ has experience on data-driven identification methodologies and implementation of data driven control strategies in real systems since 2012, with related research published since 2016. Both theoretical research and practical implementation have been carried out over the past years on several testbeds.
All this work consolidated a significant experience in Machine Learning-based data-driven techniques for identification, fault detection and control. UNIVAQ will contribute to the development of data-driven models and related methodologies and intends to significantly advance the state of the art in the reliability and failure detections in Battery Management Systems.
- Define the more appropriate requirement’s specification format and support the definition of the more appropriate validation testing methods.
- Develop data-driven methodologies to perform Prognostic and Health Management (PHM) of electronic components of the electric vehicle (ABS, BMS, etc.) based on machine learning algorithms.
- Investigate the aging of CMOS based electronics circuits and interfaces subjected to thermal cycling conditions and design a fully integrated circuit (IC) in CMOS technology optimized for batteries management in hash environments.
- Adapt a monitoring system to collect, at run-time, reliability data related to the system behaviour in order to feed the data-driven models developed.