Current research

·Semi-supervised regression models for soft sensors applications
Role: Post-Doctoral Researcher
Host institutions: University of Coimbra (UC); Institute of Systems and Robotics (ISR).
Financing: Foundation of Science and Technology (FCT), Grant reference - SFRH/BPD/112774/2015.

Summary: Soft sensors are inferential models that use on-line available sensors (e.g. temperature, flow rate, etc) to predict quality variables which cannot be automatically measured at all, or can only be measured at high cost, sporadically, or with high delays (e.g. laboratory measurements). They are important tools for many industrial processes, like pulp and paper mills, cement kiln, just to give few examples. There are many difficulties in designing soft-sensors in non-stationary scenarios (a common characteristic in many industrial plants). The post-doc research will focus on the developemnt of semi-supervised soft sensors strategies for model learning. Another objective is to validate the proposed methodologies in real case applications from different soft sensors scenarios.

Ongoing Results:
[1]. Francisco A. A. Souza, Rui Araújo, and Jérôme Mendes. Review of soft sensors methods for regression applications. Chemometrics and Intelligent Laboratory Systems, 152:69–79, March 2016. [doi; pdf; bib]

·KhronoSim - System for Simulation and Test of Complex Systems
Role: Team Member.
Host institutions: University of Coimbra (UC); Critical Software, SA; Institute of Engineering of Porto.
Financing: co-financing by “Portugal 2020” (PT2020), in the framework of the “Competitiveness and Internationalization Operational Program” (COMPETE 2020), and by the European Union through the European Structural and Investment Funds (ESIF).

Summary: Concepts such as “Fourth Industrial Revolution (Industry 4.0)” and “Internet of the Things (IoT)” boasted into the technology speech like a blizzard, touching those who use and interest themselves of technology almost as much as those developing it. Such concepts are not surprisingly more used than understood; more are those using the concepts than those actually understanding their implications. Surprisingly enough, the increase of use of technology by the population at large, makes that security is not the least well-known aspect, though still not fully grasped however. Less well-known are the implications of complex systems working tightly coupled, with little or no human intervention, or possibility of human intervention, whatsoever. In such a scenario, testing components individually, one-by-one, is not sufficient to assert the correct functioning of the overall system. KhronoSim aims at developing a platform for testing cyber-physical systems in closed-loop. A platform that is modular, extensible and usable in multiple application domains. A platform featuring hard-real-time control, enabling the integration of simulation models to build a closed loop test environment and allowing the use of physical and virtual systems alike. The application case of the project is the simulation, control, and test of a sun-synchronous satellite.

Ongoing Results: