A high-frequency sampling monitoring system for environmental and structural applications

Abstract

High-frequency sampling is not only a prerogative of high-energy physics or machinery diagnostic monitoring: critical environmental and structural health monitoring applications also have such a challenging constraint. Moreover, such unique design constraints are often coupled with the requirement of high synchronism among the distributed acquisition units, minimal energy consumption, and large communication bandwidth. Such severe constraints have led scholars to suggest wired centralized monitoring solutions, which have only recently been complemented with wireless technologies. This article suggests a hybrid wirelesswired monitoring system combining the advantages of wireless and wired technologies within a distributed high-frequency-sampling framework. The suggested architecture satisfies the mentioned constraints, thanks to an ad-hoc design of the hardware, the availability of efficient energy management policies, and up-to-date harvesting mechanisms. At the same time, the architecture supports adaptation capabilities by relying on the remote reprogrammability of key application parameters. The proposed architecture has been successfully deployed in the Swiss-Italian Alps to monitor the collapse of rock faces in three geographical areas. ACM Reference Format:Alippi, C., Camplani, R., Galperti, C., Marullo, A., and Roveri, M. 2013. A high-frequency sampling monitoring system for environmental and structural applications.

Making Intelligent the Embedded Systems Through Cognitive Outlier and Fault Detection

“…We evaluated the effectiveness of the proposed solution on a synthetically generated non-linear dataset and on a real-world dataset acquired by a sensing unit of the rockcollapse forecasting system described in [1,2]. We compare the proposed solution (denoted by COFD) with the method where no outlier or fault detection mechanisms have been adopted (denoted by B and considered here as a baseline), with the method where only the outlier detection and mitigation phase are considered (denoted by COD), and with the method encompassing only the HMM-CDT (denoted by CFD) without any outlier detection/mitigation phase.…”

“…the trained nominal conditions have to be promptly detected and suitably mitigated by differentiating among the occurrence of an outlier, a fault or model bias. The first step of the proposed solution refers to the characterization of the temporal and spatial relationships present in Z N through the learning of a dependency graph  = (V, E), where V =  is the set of sensors of the intelligent embedded system and E is a set of directed edges connecting sensors defined f (3,2) f (4,1) f (4,2) as follows:…”

Intelligence for Embedded Systems

“…Given the risk insisting in the area a fairly complex sensor network has been designed and deployed at the Rialba towers [218,219,230] to monitor the area. Since the towers are exposed to a rock toppling risk the sensor network is composed of two parts, the lower investigating insurgence of microacoustic emissions associated with the coalescencing of fractures, the upper inspecting for enlargement of the More specifically, a hybrid sensor network is the technology envisaged at the base of the towers.…”

“…Assume that we have deployed the monitoring system that, once operational, provides the information we need to assess/infer a potential environmental risk, e.g., see [142,143].…”

An Ensemble of HMMs for Cognitive Fault Detection in Distributed Sensor Networks

“…APP D2: Rialba Data. We consider data coming from a real-world distributed sensor network for rock-collapse forecasting [23,24]. This dataset is available at [25].…”