Development of a Generator Prognostic Tool

In the past decades, significant improvements in generator diagnostics were made possible by using continuous online measurements and a number of periodic tests. In recent years, the data provided has been converted into more useful information thanks to integrated diagnostic systems. For example, an integrated methodology for generator diagnostics (MIDA) was developed at Hydro-Quebec's research institute (IREQ) using a Web-based application. This comprehensive diagnostic system gives the degradation state of generator stator winding insulation by using a portfolio of diagnostic tools. Combining the various results leads to a health index ranging from 1 (good condition) to 5 (worst condition). This system is used by power plant managers as well as technical support and maintenance engineers at Hydro-Quebec in the context of condition-based maintenance (CBM). The next step of development is to add new prognostic-related characteristics. This involves automatic identification of active failure mechanisms, root cause analysis and estimation of the stage of advancement of any active mechanism. These characteristics form the basis of predictive maintenance and support the optimization of maintenance strategies. The approach chosen is based on a number of cause-and-effect chains formed by the combination of sequential physical degradation states that ultimately lead to failure. Each combination of physical states is unique and defines a particular failure mechanism. Failure mechanism analysis was followed by identification of all observable symptoms (diagnostics from MIDA) for each physical state. This paper presents a first step toward the development of a prognostic tool, where the modeling of failure mechanisms is combined with automatic analysis of observable symptoms from our diagnostic system. It puts forward probable failure mechanisms for a given generator.