An ontology framework for intelligent sensor-based building monitoring Michael Dibley, Haijiang Li ⁎, Yacine Rezgui, John Miles Engineering School, Cardiff University, UK abstract article info Article history: Accepted 30 May 2012 Available online 28 July 2012 Keywords: OntoFM Ontology Sensor system Multi-agent software Contemporary building management is highly complex. Real time building information collected from various sen- sors needs to be managed smartly and promptly, and the corresponding software system ideally should have enough intelligence to consume these inter-connected and domain oriented information in an autonomous way. This paper focusses on the ontology development process to deliver an intelligent multi-agent software framework (OntoFM) supporting real time building monitoring. Different ontology development methodologies and frameworks have been reviewed. These have informed the development of a building monitoring ontology framework and its underpinning ontologies (sensor ontology, building ontology, and other supporting ontologies). The resulting ontologies have been tested and validated following a two-staged approach. The development renders a system that delivers demonstrable rationality and robustness within the dynamic environment in which it operates. The capture of semantics through formal expression to model the environment adds a richness that the agents exploit to intelligently determine behaviours to satisfy goals that are flexible and adaptable. The developed building monitoring software framework has been deployed in several locations for testing purposes, and demonstrates the potential for larger scale deployments. © 2012 Elsevier B.V. All rights reserved. 1. Introduction Buildings have often been described as complex entities involving a wide range of stakeholders drawn from a large number of disci- plines. This complexity is reflected in the continuous introduction of new procurement paths and methods, construction technologies, materials, and construction methods, to meet various economic, envi- ronmental and societal challenges [1]. Buildings are in fact complex systems involving several forms of interactions within and across systems, sub-systems and components which translate into patterns of structure and behaviour. The understanding and modelling of these patterns of structure and behaviour can only be approached by adopting a holistic view of the building systems as opposed to focussing on analyz- ing these systems and constituent components individually [2].A systems philosophy demands that an uncoordinated approach is re- placed by a framework in which the identities of the separate parts are subsumed by the identity of the total system [3]. In engineering terms, using a systems engineering approach, the individual systems, subsys- tems and components of a building are designed and assembled together to achieve a functional and performance driven objective. Furthermore, a building systems thinking approach is necessary to understand how the different components within a building interact, the involved variables, and the dynamic forces that affect their performance. The scope of building systems is quite large, it includes the sys- tems that underpin the building (load bearing structure, the various technical services and installations, and their controls), the internal environment in terms of building usage and occupants, and the exter- nal environment in terms of site geology, climate, and physical struc- ture of the surrounding built environment. In fact, recent thinking stresses the importance of the notion of the human (i.e. building occupant) being an integral part of the system, as opposed to being considered outside of the system [4]. Moreover, building systems modelling needs to factor in the increasing and changing demand of building occupants and ways in which they interact with the various systems that compose a building facility. These occupants will poten- tially change over the lifetime of a building as this will be subject to different tenants, usages, and transformations. It is important to rec- ognize that a building is a complex dynamic system and to develop the theoretical underpinning that will result in formal information and knowledge structures and methods for their design, construction, maintenance/operation that address the uncertainties of future sce- narios as elaborated later in the paper. In this context, a good building monitoring system should be able to have an accurate understanding of “building” static information as well as to “sense” those dynamic and evolving characteristics, and to either make the appropriate preliminary decisions directly and autonomously or to further relay the corresponding information/ knowledge to humans to assist in their final decision making. Nowa- days, sensors are widely utilized in buildings to collect different infor- mation in real time, such as temperature, light, humidity etc. Sensor units are becoming very compact whereby several individual sensors can be easily assembled together to form a multi-functional e.g. wire- less ZigBee [5] based sensor unit. The information collected from Automation in Construction 28 (2012) 1–14 ⁎ Corresponding author. E-mail address: lih@cardiff.ac.uk (H. Li). 0926-5805/$ – see front matter © 2012 Elsevier B.V. All rights reserved. doi:10.1016/j.autcon.2012.05.018 Contents lists available at SciVerse ScienceDirect Automation in Construction journal homepage: www.elsevier.com/locate/autcon