A New Risk Management Methodology for Infrastructure Based on Real-Time Monitoring and Dynamic Interventions: An Example Application on an Air Handling Unit

Abstract

For an effective risk management of complex buildings it is required to dynamically estimate the risk on the service and take proper responsive measures to contrast it. This implies being able to estimate the evolving probabilities of failures over time and the way their occurrence is trust in affecting the service. This is now possible thanks to the advent of new sensing technologies and data-driven models to estimate failure probabilities, as well as solid risk management methodologies to estimate their effect on the service. However, it needs to be considered that the implementation of a dynamic risk management in standard building operation has to consider the reconfiguration of some processes to include the use of enabling technologies. In this paper a new dynamic risk management methodology is proposed to consistently (i) model the service, estimate the risk, first (ii) statically, using fault tree analysis, and then (iii) dynamically, using sensing technologies for data gathering and data-driven models for dynamic probability estimate, and finally (iv) implement the required intervention measures to minimize the risk. Then an application of the methodology is presented, for the risk management of an air handling unit, using a convolutional neural network, and its outcomes discussed. Conclusions are also drawn on the implications of integrating such a methodology in the current whole building risk management process and several outlooks are proposed.