Around 40% of the energy used in buildings is wasted as a result of inefficient operating and maintenance of the HVAC systems. Various approaches, such as automated fault detection and diagnosis (AFDD) and retro-commissioning are used to detect faults and minimize waste in HVAC systems. However, either they aim to identify failures (e.g., AFDD) after they occur or wait for the assessment period to arrive (e.g., retro-commissioning), both of which result in energy waste until problems are discovered. The facilities management industry needs approaches that help them to continuously monitor their systems, observe changes in expected pattern of behavior and pinpoint such changes before failures or large scale equipment replacements occur. The advances in the data science field provide opportunities to be leveraged towards information extraction from building operation data and investigation of the expected and actual behavior of systems. The objective of this paper is to enable automated analysis of the behavioral patterns of major HVAC equipment over time and assist in detection of variations in the system behavior that are not expected. As an initial case analysis, performance data (e.g., air temperature, valve status, air flow, etc.) of an air handling unit in a campus facility has been analyzed to identify the frequently occurring behavioral patterns and associated energy use. The initial results reveal the characteristic behavior of the system and the variations of these patterns over years to help the facility operators to pinpoint unexpected changes in system behavior and eliminate energy waste associated with such changes.