An approach to generating summaries of time series data in the gas turbine domain

In this paper, we propose an approach for generating summaries of time series data in the gas turbine domain using AI techniques. Through the think-aloud method with the aid of visualization of temporal data using time series workbench (TSW), both domain knowledge from experts about how to solve problems in the gas turbine and information about how domain experts analyze the archived temporal data are gotten. An algorithm to select interesting events is proposed and a prototype knowledge-based system is designed to generate summary of temporal data for interesting events in the gas turbine domain. Some further research works are also pointed out.