Abstract
The inspection of power generators is a critical activity that will grow in importance during the next decades as operators are seeking solutions to continuously reduce outage duration and improve availability and reliability of the equipment. Automatic and systematic data collection on the status of health of the generator enables the possibility to implement predictive diagnostic/maintenance strategies and reduce the downtime due to repair activities. In this context robotic inspections play a crucial role since they allow a quick and efficient method to acquire data on the status of the generator. This paper describes an innovative robotic system that, thanks to a novel multi-sensor analysis method, is able to inspect and evaluate the overall status of power generators. The detection system, which is located on board a crawler robot, consists of inspection cameras, a micro-hammering system that is able to detect the acoustic response of fixing components of the generator bars and an Electromagnetic Core Imperfection Detection (EL-CID) sensor, which aims to detect insulation failures. Additionally, there is a description of how the robot has been designed to be adaptable to a wide range of different generators, and how it was tested and validated in the field.
