Back to Search
Start Over
Comparative analysis of service life prediction methods applied to rendered façades
- Source :
- Materials and Structures. 49:4893-4910
- Publication Year :
- 2016
- Publisher :
- Springer Science and Business Media LLC, 2016.
-
Abstract
- This paper describes and summarizes the various models previously applied to service life prediction of rendered facades. The main methodologies are divided in four categories: (i) deterministic methods; (ii) factorial methods; (iii) stochastic methods; and (iv) artificial intelligence based models. The estimated service life obtained through these models is analysed and the models compared. The predictive ability of the models is also examined and, using ROC curves, the sensitivity and specificity of the models is analysed, evaluating the accuracy of the models in the classification of the case studies that have or have not reached the end of their service life. This study addresses a comparative analysis of the service life prediction models, regarding the predictive ability of the models, analysing the errors and the probability of failure of each model, the results obtained using the models and their ability to describe the loss of performance of rendered facades.
- Subjects :
- Engineering
Factorial
Engineering drawing
Receiver operating characteristic
business.industry
020209 energy
0211 other engineering and technologies
02 engineering and technology
Building and Construction
Machine learning
computer.software_genre
Probability of failure
Mechanics of Materials
Prediction methods
021105 building & construction
Service life
0202 electrical engineering, electronic engineering, information engineering
General Materials Science
Sensitivity (control systems)
Artificial intelligence
business
computer
Predictive modelling
Civil and Structural Engineering
Subjects
Details
- ISSN :
- 18716873 and 13595997
- Volume :
- 49
- Database :
- OpenAIRE
- Journal :
- Materials and Structures
- Accession number :
- edsair.doi...........962c5eb14f24b704fa6a36e1ed3442af
- Full Text :
- https://doi.org/10.1617/s11527-016-0832-6