Expert panel on in-situ visual inspections for masonry churches maintenance stage

The incorporation of protocols in heritage building preservation is important for the definition of preventive conservation actions. Such integration is needed to avoid restoration actions and to promote preventive maintenance instead of corrective maintenance actions. This paper presents the application of an innovative digital management system using artificial intelligence that can quantify the suitability of a sample. This kind of application can support the maintenance management of buildings and minimise human error in data collection. The fuzzy system showed slight differences between the members of the expert panel during the in-situ visual inspection. These results indicate that, despite differences between various experts' evaluation of a building, the proposed digital method helps minimise the uncertainty in the results. The paper highlights input variables, which present high dispersion (load state modification, fire and oc-cupancy), and input parameters, which present low dispersion (preservation, roof design and overloads). Fuzzy systems can adequately manage the uncertainties associated with different experts' assessment of sample that present constructive homogeneity. This study can give advantages to stakeholders during the inspection, diagnosis and evaluation stages in the improvement of mitigation policies focused on preventive maintenance programs dedicated to the resilience of heritage buildings, specifically churches emplaced in Chile. © 2021 The Author(s). Published by Vilnius Gediminas Technical University