Increasing offshore wind energy capacity together with a demand for maximum reliability raises the need for structure and machine maintenance based on (semi-)automated inspections. Smart maintenance of mechanical constructions1 does already exist but machine maintenance is behind. Recently, Soete Laboratory developed a toolkit for labscale machine monitoring as a proof of concept within the IOF StarTT-project ReViDaP-1.0 (F2016/IOF-StarTT/351). The present project ReViDaP-2.0 aims at early defect detection of gears in wind turbine (WT) gearboxes using remote in-line optical system, and real time monitoring of the damage evolution. This will enable efficient gearbox maintenance, minimize downtime and limit necessary spares. The toolkit (hardware and software) of ReViDaP-1.0 will be updated and upscaled from labscale to real scale gearboxes. This means that the optical train will be adapted for real scale WT gearboxes and the damage classification tool (software) will be standardized. The outcome of ReViDaP-2.0 must lead to a protectable technology that will form the basis for creating an independent condition monitoring service company.