Abstract
A combination of neural networks and genetic algorithms has been used to design a TRIP assisted steel in which the silicon concentration is kept low. In this context, the steel has a novel microstructure consisting of δ ferrite dendrites and a residual phase which at high temperatures is austenite. This austenite can, with appropriate heat treatment, evolve into a mixture of bainitic ferrite and carbon enriched retained austenite. The steel has been manufactured and tested to reveal a tensile strength of ∼ 1 GPa and a uniform elongation of 23%.