A Novel Cognitive Cycle for Fault Diagnosis in Infrastructural Systems

Remote sensing techniques are being increasingly used for periodic structural health monitoring of vast infrastructures such as power transmission systems. The current efforts concentrate on analysis of visual and other signals captured from the sensing devices, to diagnose the faults. Such data collection and analysis is expensive in terms of both computational overheads as well as towards robotic maneuvering of the data collection platform, such as a UAV. In this paper, we model the data gathering platform as an intelligent situated agent, and propose to autonomously control its data gathering and analysis activities through a cognitive cycle, to optimize the cost of efforts in identifying the faults that may exist. In this context, we explore use of less expensive qualitative reasoning with the background knowledge expressed as a Qualitative Bayesian Network (QBN). We introduce a reactive, economical planning algorithm around QBN that controls the sequence of data collection and analysis, much like how human inspectors do. We substantiate our claims with the results of simulation of the corresponding cognitive cycle.