AFDD improves efficiency of water network

Automated Fault Detection Diagnostics (AFDD) is a measurement science which has traditionally been used in Heating Ventilation and Air-Conditioning (HVAC) systems to identify and rectify faults; often resulting in significant energy savings (10 – 30% of energy costs). Detecting faults at the earliest possible stage can lead to reduced maintenance costs and increase the efficiency of water supply systems. AFDD tool types include: 1. Rule based AFDD utilises simple logic applied to the water network to decide whether any given system is operating as designed or not e.g. a fault could be identified if there are two identical pumps servicing the same load in a building, yet consuming different amounts of energy. Traditional flow metering may not detect such issues. 2. Model based AFDD can be segregated into Law-driven and Data-driven models. Law-driven or forward models apply physical laws to the system to forecast its operation under a given set of conditions. Data-driven or inverse models require the actual water usage trends to be quantified and characterised using data obtained from the relevant building. Comparison of the building’s real-time water usage to the Law and Data-driven models can identify faults, their severity and enable rapid diagnosis. To date, these AFDD tools have not been applied systematically to water supply infrastructure. Waternomics will develop and implement AFDD tools that can be applied to water networks in the pilots, which have been described in previous posts, that target various end users/stakeholders as follows; (i) Domestic users in Thermi, Greece (ii) A corporate operator in Linate airport, Italy and (iii) a Municipal water based demonstration in NUI Galway Engineering Building (a university building) and a school in Galway City (both in Ireland). It is expected that AFDD tools developed in this project, in conjunction with other innovative sensor equipment being developed in Waternomics will significantly enhance a number of key areas including; (i) leak detection in both commercial and household premises, (ii) link with data driven models to detect and diagnose mechanical and electrical faults in water networks, and in turn enable cost reduction due to inefficiencies and (iii) diagnose potential faults in sensors that may lead to inaccurate data (e.g. flow metering). The key steps involved in applying AFDD to a building are summarised in the figure below:

Flow chart outlining essential steps in applying AFDD to a building’s water network. Rounded rectangle indicates a start process, a normal rectangle indicates a process and the diamond represents a decision. NUI Galway project team: Dr. Eoghan Clifford, Dr. Daniel Coakley, Niall Chambers, Mark McCaffrey