%0 Journal Article
	%A Houda Najeh and  Mahendra Pratap Singh and  Stéphane Ploix and  Antoine Caucheteux and  Karim Chabir and  Mohamed Naceur Abdelkrim
	%D 2019
	%J International Journal of Architectural and Environmental Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 154, 2019
	%T Performing Diagnosis in Building with Partially Valid Heterogeneous Tests
	%U https://publications.waset.org/pdf/10010825
	%V 154
	%X Building system is highly vulnerable to different kinds
of faults and human misbehaviors. Energy efficiency and user comfort
are directly targeted due to abnormalities in building operation. The
available fault diagnosis tools and methodologies particularly rely on
rules or pure model-based approaches. It is assumed that model or
rule-based test could be applied to any situation without taking into
account actual testing contexts. Contextual tests with validity domain
could reduce a lot of the design of detection tests. The main objective of this paper is to consider fault validity when
validate the test model considering the non-modeled events such
as occupancy, weather conditions, door and window openings and
the integration of the knowledge of the expert on the state of the
system. The concept of heterogeneous tests is combined with test
validity to generate fault diagnoses. A combination of rules, range
and model-based tests known as heterogeneous tests are proposed
to reduce the modeling complexity. Calculation of logical diagnoses
coming from artificial intelligence provides a global explanation
consistent with the test result. An application example shows the efficiency of the proposed
technique: an office setting at Grenoble Institute of Technology.
	%P 643 - 648