Please use this identifier to cite or link to this item:
|Author(s):||João Mendes Moreira|
|Title:||Online failure prevention from connected heating systems|
|Abstract:||Many water boiler manufacturers are not able to detect theoccurrence of failures in the machines they produce before they can poseinconvenience and sometimes danger for costumers and workers. Moreover,the number of boilers that have to be monitored, are many times inthe range of the thousands or even millions, proportionaly to the numberof costumers a company possesses. The detection of these failuresin real time, would provide a significant improvement to the perceptionthat consumers have of a certain company, since, if these failures occur,maintenance services can be deployed almost as soon as a failure happens.In this paper, an application prototype capable of monitoring andpreventing failures in domestic water boilers, on the fly, is presented.This application evaluates measurements which are performed by sensorswithin the boilers, and identifies the ones that greatly differ fromthose received previously, as new data arrives, detecting tendencies whichmight illustrate the occurrence of a failure. The incremental local outlierfactor is used with an approach based on the interquatile range measureto detect the outlier factors that should be analysed.|
|Document Type:||Artigo em Livro de Atas de Conferência Internacional|
|Appears in Collections:||FEUP - Artigo em Livro de Atas de Conferência Internacional|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.