| KEYWORD |
Deterioration forecasting based on historical visual inspection data for maintenance infrastructure planning
Thesis abroad
Reference persons GIAN PAOLO CIMELLARO
Description The existing schemes for structural inspection are mostly schedule-based, where a structure is inspected at a regular time interval according to a pre-defined maintenance plan. However, this current practice is not always efficient. The lack of an accurate predictive model prevents the infrastructure managers from moving forward to a condition-based inspection scheme. In the latter, the inspection frequency can be adjusted based on the predicted level of infrastructure deterioration.
In this research, deterioration forecasting for preventive maintenance of infrastructure systems will be investigated. Based on historical visual inspection data, new techniques based on AI and generative adversarial networks will be developed to predict the deterioration trend of infrastructures.
Deadline 17/11/2025
PROPONI LA TUA CANDIDATURA