Nadia Kinza Mouss

TL;DR: A smart algorithm allowing short-circuit faults detection and diagnosis of PV generators based on the hybridization of a support vector machines technique optimized by a k-NN tool for the classification of observations on the classifier itself or located in its margin.

TL;DR: A smart algorithm allowing reversed polarity fault diagnosis and prognosis in PV generators based on the hybridization of a support vector regression technique optimized by a k-NN regression tool for undetermined outputs is proposed.

TL;DR: A new research space was created for modeling and detection the hybrid defects, like the presence of cells open- and short-circuit within the same photovoltaic cells group, and for a small investment, a new platform was created that exposed a display screen of the database, which presented the power of the PV module production in each period.

TL;DR: A genetic algorithm based optimization is proposed for in-house production and outsourcing under a combined approach of maintenance management and production control in multi-periods plan to satisfy all demands while minimizing the generated total cost of the manufacturer over the plan horizon.

TL;DR: A new mathematical model of a faulty photovoltaic generator operation is proposed that will be used to set normal and fault operation conditions database, which will facilitate learning and classifications phases.