Empowering aerospace and defence engineers

Aircraft wind tunnel testing

• By simulating an aircraft using computational methods such as Computational Fluid Dynamics (CFD), engineers can mimic the physical domain and run virtual wind tunnel experiments for a fraction of the price. This allows aerospace engineers to understand the performance of designs in advance, thus narrowing down the right design choices for the prototype stage. 
  
  
• Build 3D AI models that directly predict rolling road wind tunnel performance of a rim from the CAD design – faster and more accurate than CFD!​
  
  
• By importing data from the sensors, test rig, and airflow, the customer can accurately predict the readings from sensors that have failed, the aerodynamic performance of the product, and the impact of air contamination on the test​.

Flight dynamics

• Predict turbulent aircraft behaviour with Monolith. ​Perform dynamics tests in 72–80% less time using Bayesian Deep Learning in a clever new way. 
  
  
• As gusts occur at many different wind speeds, flight altitudes, and for differently loaded aircraft, engineers need to manually check 1000s of scenarios – a tremendously complicated task.​ 
  
  
• With a deep neural network predicting changes in real-time as part of an interactive dashboard, this actually becomes quite fun to do.

Composite material testing

• Use existing data and handle the categorical information (type of fibres) to train machine learning models in Monolith.
  

• Quickly calculate the properties of a composite material.

• Quickly find an optimal microstructure.