Over the past century there has been a dramatic increase in the consumption of resources such as energy, raw materials, water, etc. in the manufacturing domain. An intelligent resource monitoring system that uses structural, context and process information of the plant can deliver more accurate monitoring results that can be used to detect excessive resource consumption. Recent monitoring systems usually run on a central unit. However, modern plants require a higher degree of reusability and adaptability which can be achieved by several monitoring units running on decentralized autonomous devices that allow the components to monitor themselves. To integrate structural, context and process information on such autonomous devices for resource monitoring, semantic models and rules are appropriate. This paper will present an architecture of a decentralized, intelligent resource monitoring system which uses structural, context and process knowledge to compute the state of the individual components by means of models and rules. This architecture might also be used for other manufacturing systems such as diagnostic or prognostic systems.
%0 Book Section
%1 AbeleOllingerEtAl12IRAM
%A Abele, Lisa
%A Ollinger, Lisa
%A Heck, Ines
%A Kleinsteuber, Martin
%B Trends in Intelligent Robotics, Automation, and Manufacturing: First International Conference, IRAM 2012, Kuala Lumpur, Malaysia
%C Heidelberg
%D 2012
%E Poonambalam, S. G.
%E Parkkinen, Jussi
%E Ramanathan, Kuppan Chetty
%I Springer
%K 01614 springer paper dfki embedded ai factory energy optimize zzz.cps
%N 330
%P 371--378
%R 10.1007/978-3-642-35197-6_41
%T A Decentralized Resource Monitoring System Using Structural, Context and Process Information
%X Over the past century there has been a dramatic increase in the consumption of resources such as energy, raw materials, water, etc. in the manufacturing domain. An intelligent resource monitoring system that uses structural, context and process information of the plant can deliver more accurate monitoring results that can be used to detect excessive resource consumption. Recent monitoring systems usually run on a central unit. However, modern plants require a higher degree of reusability and adaptability which can be achieved by several monitoring units running on decentralized autonomous devices that allow the components to monitor themselves. To integrate structural, context and process information on such autonomous devices for resource monitoring, semantic models and rules are appropriate. This paper will present an architecture of a decentralized, intelligent resource monitoring system which uses structural, context and process knowledge to compute the state of the individual components by means of models and rules. This architecture might also be used for other manufacturing systems such as diagnostic or prognostic systems.
%@ 978-3-642-35196-9
@incollection{AbeleOllingerEtAl12IRAM,
abstract = {Over the past century there has been a dramatic increase in the consumption of resources such as energy, raw materials, water, etc. in the manufacturing domain. An intelligent resource monitoring system that uses structural, context and process information of the plant can deliver more accurate monitoring results that can be used to detect excessive resource consumption. Recent monitoring systems usually run on a central unit. However, modern plants require a higher degree of reusability and adaptability which can be achieved by several monitoring units running on decentralized autonomous devices that allow the components to monitor themselves. To integrate structural, context and process information on such autonomous devices for resource monitoring, semantic models and rules are appropriate. This paper will present an architecture of a decentralized, intelligent resource monitoring system which uses structural, context and process knowledge to compute the state of the individual components by means of models and rules. This architecture might also be used for other manufacturing systems such as diagnostic or prognostic systems.},
added-at = {2016-05-11T13:38:56.000+0200},
address = {Heidelberg},
author = {Abele, Lisa and Ollinger, Lisa and Heck, Ines and Kleinsteuber, Martin},
biburl = {https://www.bibsonomy.org/bibtex/28fe761d69e757694e07a54b9843f58e1/flint63},
booktitle = {Trends in Intelligent Robotics, Automation, and Manufacturing: First International Conference, IRAM 2012, Kuala Lumpur, Malaysia},
doi = {10.1007/978-3-642-35197-6_41},
editor = {Poonambalam, S. G. and Parkkinen, Jussi and Ramanathan, Kuppan Chetty},
file = {SpringerPro:2012/AbeleOllingerEtAl12IRAM.pdf:PDF;Springer Pro:https\://www.springerprofessional.de/trends-in-intelligent-robotics-automation-and-manufacturing/4028290:URL},
groups = {public},
interhash = {1bcd0b410dec63464b0b5fbe75e924a8},
intrahash = {8fe761d69e757694e07a54b9843f58e1},
isbn = {978-3-642-35196-9},
issn = {1865-0929},
keywords = {01614 springer paper dfki embedded ai factory energy optimize zzz.cps},
number = 330,
pages = {371--378},
publisher = {Springer},
series = {Communications in Computer and Information Science},
timestamp = {2018-04-16T11:48:14.000+0200},
title = {A Decentralized Resource Monitoring System Using Structural, Context and Process Information},
username = {flint63},
year = 2012
}