Machine Learn with Time Series Data to Identify Abnormalities of Air Conditoner

San Francisco Bay Area Rapid Transit (BART) provides rail transportation to the Bay area.

The temperature is of vital importance to the proper operation of the train control equipment. We have air conditioners at the rooms where the equipment is housed. We must monitor and hopefully predict when the air conditioners stop working to proactively maintain the air conditioners in proper working conditions. We can monitor the room temperatures and their relationships to the outdoor temperature to determine whether the air conditioners are working properly or not. This project is to develop an algorithm to automate the detection of abnormality of the air conditioners.