Case Study: The Effective Use of an Extensive Logical Rule Based Data Analytics Approach in Establishing Root Cause of Performance Issues in Widespread Deployments of Unitary Space Air Conditioning Units

Today a significant percentage of office spaces are air conditioned using widely deployed unitary systems, either Fan Coil Units (FCU) or Variable Air Volume (VAV) boxes, to achieve high degrees of air conditioned zonal control. However establishing a near realtime overall control monitoring regime to ensure proper control adherence across such large estates can be difficult, or possibly unattainable, where the number of units could effectively run into the hundreds, if not the thousands.

And, as is outlined in the problem definition section of this paper, compounding normal operational control issues such as system tuning and hardware failures, with inbuilt design limitations and poor building fabric issues, coupled with embedded deep rooted and undetected commissioning problems, and all functioning within a dynamic operational environment, one can see that the task of effective and timely root cause analysis can be an extremely difficult one [1].

Having being challenged with such a problem environment, the author attempts, through presentation of a series of actual real life working examples, to offer the reader the case for use of an effective and efficient aggregated data driven analytical approach, which includes temporal and geo spatial visualisation techniques, that makes the identification of the fundamental root cause problems, and system interactions (positive and negative) within this complex operational environment analysis, possible.

The presented approach therefore offers the SME community a means to detect the current underlying problems without the need for deployment of costly disruptive diagnostic procedures or preventative maintenance regimes. Such an approach also demonstrates the flexibility to cater for future problem diagnosis scenarios where the underlying logical rules built within the underlying architecture can be written, tested and deployed in a timely fashion. Finally it is contended that this targeted aggregated data driven fault diagnosis approach is equally applicable in any other situation which entails wide spread deployment of energy assets, for example, high volume deployments of store refrigeration units used within the Retail sector [2].

By: Niall Brady

Published in: RC25398 in 2013

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

rc25398.pdf

Questions about this service can be mailed to reports@us.ibm.com .