Data analysis is a process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. (Wikipedia)

Analytics software is used to collect building operational data from a myriad of disparate sources including Building Management and Control Systems (BMCS), Energy Management Systems (EMS), access and security control systems, lifts and other digitally controlled building services. Importantly, we can now also link data from non-building related sources such as Computerised Maintenance Management Systems (CMMS) and Financial Management Systems (FMS), adding further dimensions to the data we collect, the analysis we can perform and the insights to be gained.

These systems provide access to thousands of pieces of performance data through real-time point monitoring (sensors, actuators, control output, and software/programs), as well as potentially thousands more computed and virtual points and static equipment design data. An Analytics platform can continuously gather, organise and validate this data to create a system-wide digital model.

Operational Analytics can support three important processes for improved outcomes in buildings; Building Energy Optimisation to reduce energy usage, Automatic Fault Detection and Diagnostics (AFDD) to preempt failures and reduce reactive maintenance spend, and Data Driven Maintenance (DDM) to prioritise and reduce preventative maintenance spend.

Building Energy Optimisation:

Through in-depth analysis of operational parameters, historical performance, and energy usage profiles, it can be determined that if plant and equipment is operating at its optimal design performance for any given set of conditions, any degradation of performance that may otherwise be masked by the adaptive nature of the BMCS can be detected.

Automatic Fault Detection and Diagnostics (AFDD):

Uses Data Analytics to detect and diagnose the root cause of equipment faults, operational inefficiencies, and predict potential system failures. By applying analytics to lead operational indicators, impending equipment failures can be identified at the earliest sign and acted on. This supports the proactive management of reactive maintenance and repairs and reduces downtime. Previous fault conditions can be used to predict future failures.

Data Driven Maintenance (DDM):

Uses the same data as for AFDD to develop a performance score for individual pieces of equipment and a performance ranking for the item against similar equipment. This ranking can then be used in conjunction with the maintenance and repair history of the equipment and its criticality to facility operations to identify and prioritise preventative and corrective maintenance activities towards the most in-need equipment.