Archives

Structural damage assessment using linear approximation with maximum entropy and transmissibility data

  • April 13, 2015
  • Comments off

Mechanical Systems and Signal Processing Vol. 54-55, pp. 210-223, 2015 V. Meruane, A. Ortiz-Bernardin Abstract Supervised learning algorithms have been proposed as a suitable alternative to model updating methods in structural damage assessment, being Artificial Neural Networks the most frequently used. Notwithstanding, the slow learning speed and the large number of parameters that need to

Read More » Read More

Paper Accepted: Structural Damage Assessment Using Linear Approximation with Maximum Entropy and Transmissibility Data

  • August 23, 2014
  • Comments off

Paper Accepted for Publication in Mechanical Systems and Signal Processing V. Meruane, A. Ortiz-Bernardin, “Structural damage assessment using linear approximation with maximum entropy and transmissibility data.” ABSTRACT Supervised learning algorithms have been proposed as a suitable alternative to model updating methods in structural damage assessment, being Artificial Neural Networks the most frequently used. Notwithstanding, the

Read More » Read More

Vibration-based damage assessment using linear approximation with maximum entropy

  • July 22, 2014
  • Comments off

14th Pan-American Congress of Applied Mechanics – PACAM XIV March 24-28, 2014, Santiago, Chile Proceedings of PACAM XIV V. Meruane and A. Ortiz-Bernardin Abstract Supervised learning algorithms have been proposed as a suitable alternative to model updating methods in vibration-based damage assessment, being Artificial Neural Networks the most frequently used. Notwithstanding, the slow learning speed and

Read More » Read More

Paper Submitted: Damage Identification Using Linear Approximation with Maximum-Entropy and Transmissibility Data

  • September 19, 2013
  • Comments off

V. Meruane, A. Ortiz-Bernardin, “Damage identification using linear approximation with maximum-entropy and transmissibility data,” submitted. ABSTRACT Supervised learning algorithms have been proposed as a suitable alternative to model updating methods in damage assessment, being Artificial Neural Networks the most frequently used. Notwithstanding, the slow learning speed and the large number of parameters that need to

Read More » Read More