Traditionally, maintenance was performed at power plants on the most critical machines on a time-based schedule; however, this often resulted in activities occurring before they were necessary. Over the past 20 years, there has been a shift in the industry towards condition-based maintenance. This strategy requires the collection of a variety of data to detect most ageing-related mechanisms, which can be used to better schedule and plan maintenance. Initially, data collection was carried out manually and performed infrequently, but once the benefits of condition monitoring started to be realised, this shifted to continuous real-time monitoring. Today, there is another shift away from application-specific software to accessing a variety of data on a common platform, allowing for a more comprehensive analysis. The most critical machines in a power plant are the turbine generator sets. The generator rotor and stator windings are generally very reliable; however, they do age over time, reducing electrical and mechanical strength. This paper focuses on detecting turbine generator rotor and stator winding problems prior to failure using an integrated approach. A case example will be discussed, which includes partial discharge, rotor flux and stator end-winding vibration
