University of Cambridge > > Engineering Department Structures Research Seminars > Machine learning as a tool to design special concrete mixes

Machine learning as a tool to design special concrete mixes

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Nishangani Gowrikanthan .

Special concretes refer to concrete mixtures designed with unique properties to achieve specific purposes beyond those of conventional concrete, such as increased strength, lighter weight, or higher permeability, among others. Due to their particular composition, existing mix design methods often lack sufficient accuracy to reliably estimate their behaviour. Consequently, complementary use of laborious laboratory tests may be required, thus increasing the consumption of time, money, and resources during structural design processes. In the last decade, the widespread use of artificial intelligence and its application in civil engineering and architecture has represented a significant step forward in gaining a better understanding of construction materials. By combining experimental data with machine learning algorithms, it has been possible to develop models that enhance existing design methodologies for special concrete mixes, and reduce the need for extensive experimental testing. This seminar will present various examples of neural network applications in the design of fibre-reinforced and pervious concrete mixes with the objective of predicting their key performance properties.

This talk is part of the Engineering Department Structures Research Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity