A Hidden Markov Models tool for estimating the deterioration level of a power transformer

In electrical power systems, asset management procedures have developed into a central element of network operations and planning. Hidden Markov models (HMM) can be used to transform various data collected from substation equipment into failure probabilities. Based on these failure probabilities a mathematical decision tool can be created, which could be used in system-level simulation and experimentation. In particular, collected data utilizing the dissolved gas analysis-in-oil (DGA) field methodology for transformers are analyzed with HMM for the prediction of their deterioration level.