10 Autoregressive Model Applied to the Meazza Stadium for Damage Detection 109 In the second part of the paper we applied an autoregressive model AR(40) to model the vibration signal acquired by an accelerometer fixed to a stand. This procedure allowed to properly describe the response of the structure to the ambient dynamic excitations. The residues demonstrated that the signal was correctly fitted when the structure is empty. It was also possible to identify some unusual working conditions of the stand, at least for the identified model, for instance during concerts and football matches, using the Mahalanobis distance applied to the coefficients of the AR model. References 1. Sohn H et al (2000) Damage diagnosis using statistical process control. Conference on recent advances in structural dynamics, Southampton, 22–25 July 2000 2. de Lautour OR et al (2009) Nearest neighbour and learning vector quantization classification for damage detection using time series analysis. Struct Control Health Monit, 17(6):614–631 October 2010 3. Box GEP et al (1994) Time series analysis: forecasting and control, 3rd edn. Prentice Hall, Englewood Cliffs 4. Wei WWS (1990) Time series analysis: univariate and multivariate methods. Addison-Wesley, Redwood City 5. Cremona E (2012) Analisi applicative di criteri per il Model Updating di strutture complesse il caso del modello di una tribuna rettilinea del terzo anello dello stadio Giuseppe Meazza. Master degree thesis, Politecnico di Milano 6. Sohn H et al (2005) Structural damage classification using extreme value statistics. J Dyn Syst Meas Control 127:125
RkJQdWJsaXNoZXIy MTMzNzEzMQ==