Details of Grant 

EPSRC Reference:	GR/J14264/01
Title:	LIFE PREDICTION OF CONCRETE STRUCTURES USING NEURAL NETWORKS
Principal Investigator:	Buenfeld, Professor NR
Other Investigators:	Jones, Professor A
Researcher Co-Investigators:
Project Partners:
Department:	Civil & Environmental Engineering
Organisation:	Imperial College London
Scheme:	Standard Research (Pre-FEC)
Starts:	25 August 1993	Ends:	24 February 1996	Value (£):	75,255
EPSRC Research Topic Classifications:
EPSRC Industrial Sector Classifications:	Construction
Related Grants:
Panel History:
Summary on Grant Application Form
Our ability to predict the service life of concrete structures would be greatly increased if better use could be made of data generated by condition surveys. The main objective of this is to assess the potential of using neural networks (NNs) for this purpose.2 NNs will be developed. They will predict chloride concentration profiles and the time to cracking due to rebar corrosion, in RC structures exposed to a marine environment. They will be trained and tested using data from real long-term exposure situations. Results will be compared with those from conventional statistical analysis of the same data. The influence of NN variables such as a number of hidden layers and hidden layer neurons, connection types, activation functions and transfer functions on the type and quantity of training data required and the accuracy fo predictions, will be investigated. Other issues investigated will include, effect of missing data, methods of imposing predefined effects of particular concrete and environmental parameters and the relative merits of concrete constituents and concrete properties as inputs.These NNs will be useful to designers of new marine structures and assessors of existing ones and could form the basis of more realistic design code durability recommendations. Most importantly, recommendations will be made concerning the circumstances under which neural networks are applicable to life prediction in general.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.imperial.ac.uk