Model-based predictive maintenance in building automation systems with user discomfort

This work presents a new methodology for quantifying the discomfort caused by non-optimal temperature regulation, in a building automation system, as a result of degraded biomass boiler operation. This discomfort is incorporated in a model-based dynamic programming algorithm that computes the optima...

Full description

Bibliographic Details
Main Authors: Cauchi, N, Macek, K, Abate, A
Format: Journal article
Published: Elsevier 2017
_version_ 1797102139135229952
author Cauchi, N
Macek, K
Abate, A
author_facet Cauchi, N
Macek, K
Abate, A
author_sort Cauchi, N
collection OXFORD
description This work presents a new methodology for quantifying the discomfort caused by non-optimal temperature regulation, in a building automation system, as a result of degraded biomass boiler operation. This discomfort is incorporated in a model-based dynamic programming algorithm that computes the optimal maintenance action for cleaning or replacing the boiler. A non-linear cleaning model is used to represent the different cleaning strategies under taken by contractors. The maintenance strategy minimizes the total operational costs of the boiler, the cleaning costs and the newly defined discomfort costs, over a long-term prediction horizon that captures the short-term daily thermal comfort within the heating zone. The ap- proach has been developed based on real data obtained from a biomass boiler at a Spanish school and the resulting optimal maintenance strategies are shown to have the potential of significant energy and cost savings.
first_indexed 2024-03-07T06:01:41Z
format Journal article
id oxford-uuid:ec68325a-5f1c-4ee3-8297-5ead8fee8623
institution University of Oxford
last_indexed 2024-03-07T06:01:41Z
publishDate 2017
publisher Elsevier
record_format dspace
spelling oxford-uuid:ec68325a-5f1c-4ee3-8297-5ead8fee86232022-03-27T11:17:15ZModel-based predictive maintenance in building automation systems with user discomfortJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ec68325a-5f1c-4ee3-8297-5ead8fee8623Symplectic Elements at OxfordElsevier2017Cauchi, NMacek, KAbate, AThis work presents a new methodology for quantifying the discomfort caused by non-optimal temperature regulation, in a building automation system, as a result of degraded biomass boiler operation. This discomfort is incorporated in a model-based dynamic programming algorithm that computes the optimal maintenance action for cleaning or replacing the boiler. A non-linear cleaning model is used to represent the different cleaning strategies under taken by contractors. The maintenance strategy minimizes the total operational costs of the boiler, the cleaning costs and the newly defined discomfort costs, over a long-term prediction horizon that captures the short-term daily thermal comfort within the heating zone. The ap- proach has been developed based on real data obtained from a biomass boiler at a Spanish school and the resulting optimal maintenance strategies are shown to have the potential of significant energy and cost savings.
spellingShingle Cauchi, N
Macek, K
Abate, A
Model-based predictive maintenance in building automation systems with user discomfort
title Model-based predictive maintenance in building automation systems with user discomfort
title_full Model-based predictive maintenance in building automation systems with user discomfort
title_fullStr Model-based predictive maintenance in building automation systems with user discomfort
title_full_unstemmed Model-based predictive maintenance in building automation systems with user discomfort
title_short Model-based predictive maintenance in building automation systems with user discomfort
title_sort model based predictive maintenance in building automation systems with user discomfort
work_keys_str_mv AT cauchin modelbasedpredictivemaintenanceinbuildingautomationsystemswithuserdiscomfort
AT macekk modelbasedpredictivemaintenanceinbuildingautomationsystemswithuserdiscomfort
AT abatea modelbasedpredictivemaintenanceinbuildingautomationsystemswithuserdiscomfort