The objective of this thesis, situated in the field of human-centered artificial intelligence, is to develop a formal and tooled approach for reasoning assistance in the presence of inconsistent information, framed in belief function theory.
The aim of this project is to adopt a transdisciplinary approach by focusing in particular on the supply chain of seafood products and its optimization in the context of a circular economy and strong human pressures exerted on marine ecosystems.
The main objective of this thesis is to develop machine learning approaches to detect faults in the motor/converter combination in an electric drive train. The data will be time series of sensor measurements. One can think of values of current, voltage, vibration, magnetic field, speed, temperature, ...