ABSTRACT
Data driven energy centered maintenance is the main component in developing a digitally enabled maintenance approach. Implementing the model allows the building operators to automate more than 50%-60% of the energy-related maintenance tasks, which increases the accuracy of predictive maintenance, reducing maintenance man-hours and expanding the equipment reliability, energy efficiency, and lifespan. The current digital evolution trend that involves data driven decision-making has opened new opportunities for energy centered maintenance. The utilization of artificial intelligence and machine learning in energy centered maintenance are capable of monitoring the equipment’s current performance, collecting operational data, analyzing it, and identifying if there is any performance variation in its current condition compared to the required performance level. The dominant reason for automating energy centered maintenance tasks is the use of equipment’s primary operational data and real-time machine that quantifies when and what kind of maintenance is needed to maintain, repair, or replace critical parts within the equipment.
