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.
 Crawley, F. and Tyler, B . (2015). HAZOP: Guide to Best Practice.
 Galar,D,; Thaduri, A,; Catelani, M,; and Ciani, L. Context awareness
for maintenance decision making: A diagnosis and prognosis approach.
Measurement 2015, vol. 67 0263-2241.
 L. Scanu, S. Ploix, P. Bernaut and E. Wurtz (2017). Towards new model
based energy management services. In IBPSA San-Francisco.
 Najeh, H., Singh, M. P., Chabir, K., Ploix, S., & Abdelkrim, M. N. (2018).
Diagnosis of sensor grids in a building context: Application to an office
setting. Journal of Building Engineering, 17, 75-83.
 Ploix, S. Des systèmes automatisés aux systèmes coopérants: application
au diagnostic et à la gestion énergétique. Habilitation à diriger des
recherches (HDR) 2009, chapter 3 and 5, 43-51.
 Reiter, R. A Theory of Diagnosis from First Principles. Artificial
Intelligence 1987, vol. 32 (1) 57-95.
 Singh, Mahendra, Stéphane Ploix, and Frédéric Wurtz (2016). Handling
Discrepancies in Building Reactive Management Using HAZOP and
Diagnosis Analysis. ASHRAE. St. Louis, MO, 8.
 Singh, M. Improving building operational performance with reactive
management embedding diagnosis capabilities. PhD. Thesis University
of Grenoble Alpes 2017
 Zhang, W., Zhao, Q., Zhao, H., Zhou, G., & Feng, W. (2018). Diagnosing
a Strong-Fault Model by Conflict and Consistency. Sensors, 18(4), 1016.