The main goal of this project is to develop expert intelligence tools to be incorporated in commercial energy management platforms for proactive energy management in buildings to further optimize energy savings. To this end, three (3) fuzzy logic powered tools will be deployed to be incorporated in well-known SaaS platforms used for energy management to further improve decision making related to smart fault detection and diagnostics as well as intelligent predictive maintenance of basic equipment as follows:
- an expert FDD analyser,
- an HVAC system optimizer, and
- a maintenance expert.
Proactive fault diagnostics is the process of proactively manipulating system inputs to perform a diagnostic test. It consists of a diagnostic part and a proactive testing part. The proactive testing part manipulates/directs the input and the diagnostic part analyses the output to assess the system’s health status. The goal of proactive testing is to control adjustable parameters—for example, set-point, mode, schedule, damper position, fan speed, and so on—to facilitate and complete the diagnostic process. Fuzzy logic has turned out to be a popular choice for these types of problems. The inherent flexibility embedded in fuzzy sets and fuzzy rules make it a suitable solution for reasoning in domains affected by uncertainty and error. In building HVAC systems, fuzzy-based diagnostic mechanisms have been used in several studies. In this project, during the implementation of our expert FDD analyser we will develop fuzzy-based diagnostic routines for fault detection and diagnosis of various units of common building equipment, such as HVACs, PV plants, pumps, etc. In our approach, fuzzy-based inference mechanisms will compare system outputs with the predictions of simplified models at various operating points to draw conclusions about the system health status.
On the other hand, next generation BEMSs will help building owners to better manage the performance of their buildings, anticipate potential for savings or HVAC issues before they happen, and shift operations and maintenance team efforts from reactive to proactive systems management. Besides, solution providers have a specific interest in meeting the needs of smaller facilities. Vendors from the traditional automation and control segment, IT and niche specialty providers have identified HVAC system optimization as a specific avenue through which BEMSs can support smaller facilities. For instance, to decrease the energy consumption researchers in the area of thermal comfort have learned that the required indoor temperature of a building is not a fixed value. In fact, the certain range of temperatures is sufficient to create a comfortable situation. Therefore, the ideal HVAC system works with high efficiency supplying only the amount of heat, cold and air that is necessary to maintain internal conditions at a level providing thermal comfort to room occupants. In this project, users can benefit from more savings with the advanced features of our HVAC system optimizer - based on a fuzzy inference engine -, such as operating set point adjustment, inference control for variable frequency drives, etc.
Finally, when building system components unexpectedly fail, you face costly downtime and unsatisfiedoccupants. With predictive maintenance, you’ll identify potential hidden problems prior to breakdowns and proactively schedule repairs at times that won’t inconvenience you or your building’s occupants. Furthermore, predictive maintenance helps you control energy costs, prolong equipment life and prevent overtime costs for unscheduled repairs. With an expert system the status and past maintenance history of basic building equipment are used to do the work in a thorough and consistent manner. An expert system for predictive maintenance requires several functions to make it usable to a building owner or professional, including configuration ability, site visit types, user interaction, explanations, graphics, context sensitivity, displaying readings, logging conditions, deferring work, reports, comments and display. Whether this expert system is successful or not depends on an additional important factor: to take into account the availability of a real expert in the discipline, familiar with all operations and problems with the building systems services. In this project, our maintenance expert will be a fuzzy logic expert tool to predict future maintenance needs of basic building equipment by leveraging past performance, logging conditions, reports, prior FDD analysis, ESCOs knowledge and support, etc.