Material design
Unique deep learning toolset for design and data validation

Intellegens suite off tools allow training of neural networks on internal datasets to generate predictive models that can be applied in design process or for data validation.

In house or online
Compiled code available for intergration in internal workflows or fully hosted solutions.

A range of software tools available to fit all recquirements. Full stack solutions with easy install for internal systems or web based subscription model with on demand compute to scale for any data

More arrow
More arrow

Novel deep learning toolset

Intellegens unique neural network algorithm is especially well suited to model and verify material properties. The neural network algorithm has a unique capability to handle incomplete data sets in both training and predicting, can exploit composition-property and property-property correlations to enhance the quality of predictions, and can also handle a graphical data as a single entity. The framework is tested with different validation schemes, and then applied to materials case studies of alloys and polymers.

 

Materials data example

There are millions of materials available, with data on these materials is spread out and incomplete.

Identifying the correct material early will lead to better product and significant reductions in time and cost.



Material ID
Hardness
Density
Melting Point
Conductivity
Cost
% Carbon
% Silicon
Heat treatment
100110021003
50 323
22 18
26023821
330k
5.27 52.15
0.1 0.4
4.5 2.1
800 1150
ZZ9F1ZZ9F2
50 323
50 323
50 323
- -
50 323
0.1 -
0.1 -
800 -
A2182Z8A2282Z9
50 32350 323
50 .50 1
. 323. 323
232 .232 0.9
50 32350 323
. 323. 323
232 .232 0.9
. 323. 323


Papers and Patents

read more More arrow

Design of a molybdenum-base alloy using a neural network

November 2017
read more More arrow

Design of a nickel-base superalloy using a neural network

October 2017

Please get in touch to see how we can help

See how our unique AI can solve real world problems