The paper proposes a hybrid technique to solve the inverse problem of damage localization and severity estimation in beam structures. The first phase of the method involves the use of influence lines (IL) to extract information about the damage location. Then, a genetic algorithm (GA), representing the core of the whole procedure, utilizes static parameters as displacements and rotations at few points to evaluate the bending stiffness along the structure by updating a finite element model. The information obtained in the first phase is used in the second phase for: (i) reducing the number of design variables of the GA and the consequent computational time; (ii) improving the accuracy of GA solutions because it allows a suitably trained neural network to select proper values for the coefficients of the proposed cost function inside the genetic algorithm. The procedure is applied to a test problem, namely a simply supported, prestressed concrete railway bridge, located in northern Italy. Numerical experiments are also conducted to test the procedure when the beam length and geometric properties vary.

Genetic algorithm supported by influence lines and neural network for bridge health monitoring / Marasco, Giulia; Piana, Gianfranco; Chiaia, Bernardino; Ventura, Giulio. - In: JOURNAL OF STRUCTURAL ENGINEERING. - ISSN 1943-541X. - STAMPA. - (2022). [10.1061/(ASCE)ST.1943-541X.0003345]

Genetic algorithm supported by influence lines and neural network for bridge health monitoring

Marasco, Giulia;Piana, Gianfranco;Chiaia, Bernardino;Ventura, Giulio
2022

Abstract

The paper proposes a hybrid technique to solve the inverse problem of damage localization and severity estimation in beam structures. The first phase of the method involves the use of influence lines (IL) to extract information about the damage location. Then, a genetic algorithm (GA), representing the core of the whole procedure, utilizes static parameters as displacements and rotations at few points to evaluate the bending stiffness along the structure by updating a finite element model. The information obtained in the first phase is used in the second phase for: (i) reducing the number of design variables of the GA and the consequent computational time; (ii) improving the accuracy of GA solutions because it allows a suitably trained neural network to select proper values for the coefficients of the proposed cost function inside the genetic algorithm. The procedure is applied to a test problem, namely a simply supported, prestressed concrete railway bridge, located in northern Italy. Numerical experiments are also conducted to test the procedure when the beam length and geometric properties vary.
File in questo prodotto:
File Dimensione Formato  
Marasco_Piana_Chiaia_Ventura_author's_accepted_manuscript.pdf

non disponibili

Descrizione: Articolo versione accettata (R1)
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 4.05 MB
Formato Adobe PDF
4.05 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2954155