Centro tecnológico Cartif

Intelligent preservation and maintenance of infrastructures

By applying Computational intelligence (CI) techniques to the transport infrastructure maintenance area, both roads and railways, it is intended to make valuable for the companies of the sector the information, knowledge, and experience the have gathered along the way, which are not systematically put into good use for multiple reasons.

The techniques to use have proven to be valid in both academic and, in some cases, industrial fields, although their application within the later activity range has been almost nonexistent until this moment.

The process is developed starting form the knowledge (experience, monitoring, historic information, etc.) and available resources. A proper use, based on CI methods and similar techniques, will make possible to extract, model, and transfer knowledge that will make the involved companies able to give a higher added value to their activity and services.

Consequently, it entails research on how the CI techniques can be applied to the sector’s problems on each of the steps necessary to transfer the gathered and stored data and ideas, from an expert on the field to a computer-based system that assists the tasks of maintenance and preservation of infrastructures.

The main goals to achieve when trying to apply intelligent technologies to preservation can be summarized with the following points:

• Improve the planning of the preservation actions.
• Improve the safety and end-user accessibility conditions.
• Increase the wear-out life of the infrastructures.
• Reduce the cost of preservation and maintenance.
• Improve service quality.

Partners and Collaborators

• 
  Grupo VIAS
  (www.vias.es)
• 
  ACEX
  (www.acex.ws)
• 
  DECSAI, Granada University
  (Spain).
  (sci2s.ugr.es)

Other partners and collaborators

Related publications:

• M. Galende, G.I. Sainz, M.J. Fuente. Accuracy-Interpretability Balancing in Fuzzy Models based on Multiobjective Genetic Algorithm. Proceeding European Control Conference 2009 (ECC'09), Budapest (Hungary), August 2009.
• M. I. Rey, M. Galende, G. I. Sainz. Criteria for linguistic improvement of precise fuzzy models by orthogonal transforms. Application to ART based models. Proceedings of European Control Conference 2009 (ECC'09), Budapest (Hungary), August 2009.
• R. Garcia, J. M. Benitez, G. I. Sainz. Feature Selection for Time Series Forecasting: A Case Study. Proceeding Eighth International Conference on Hybrid Intelligent Systems, Barcelona (Spain), September 2008.
• M. J. Fuente, V. Mateo, G.I. Sainz, S. Saludes. Adaptive Neural-based Fault Tolerant Control for Nonlinear Systems. Proceedings of 17th IFAC World Congress, Seoul (Korea), July 2008.
• M. Galende, G. I. Sainz, M. J. Fuente, A. Herreros. Interpretability-accuracy improvement in a neuro-fuzzy ART based model of a DC motor. Proceedings of 17th IFAC World Congress, pp. 7034 - 7039, Seoul (Korea), July 2008.
• M. Galende, G. I. Sainz. Mejora Lingüística de Modelos Neurodifusos mediante Algoritmos Genéticos: Aplicación a un Motor DC. Actas de las XXVIII Jornadas de Automática, Huelva (Spain), September 2007. ISBN: 978-84-690-7497-8.
• G. I. Sainz, J. Juez, E. Moya, J. R.Perán, Fault detection and fuzzy rule extraction in AC motors by a neuro-fuzzy ART-based system, Engineering Applications of Artificial Intelligence, vol. 18(7) pp. 867-874, 2005.
• G. I. Sainz, M. J. Fuente P. Vega. Recurrent neuro-fuzzy modelling of a wastewater Treatement Plant, European Journal of Control, No 10, pp. 83-95, January 2004.

More information: This e-mail address is being protected from spambots. You need JavaScript enabled to view it