A collaborative team from the US Department of Energy (DOE) and Argonne National Laboratory have employed Artificial Intelligence (AI) to successfully manufacture airplane components.
What is needed to manufacture an airplane?
Manufacturing an airplane consists of new components that are both lightweight and strong, and these parts are constructed by a process known as ‘friction stir welding.’
In a new collaboration with GE Research, Edison Welding Institute and GKN Aerospace, Argonne computer scientists are putting the power of the laboratory’s automated machine learning expertise and supercomputers to use. By reducing the number of costly experiments and time-consuming simulations with a new machine learning approach, accurate models can be generated that provide valuable information about the welding process much more efficiently.
How is this new method being utilised?
This approach is called ‘DeepHyper’ and is a scalable automated machine learning package developed by Argonne computational scientist Prasanna Balaprakash and his colleagues at Argonne; machine learning is the process by which a computer trains itself to find the best answers to a particular question.
“If you’re trying to brew the best cup of coffee, you can spend several hours fiddling with the many settings on the best machines,” Balaprakash explained. “In trying to make airplane parts, we can avoid this by using machine learning, which gives us the ability to learn from a handful of example settings and identify the best one from a set of a billion possible configurations.”
According to Balaprakash, the machine learning algorithm uses a training data set of various welding conditions and parameters from which airplane part properties can be determined. From this data set, vastly more possible inputs are instantly analysed and ranked to determine which give the best possible components.
“Manufacturing airplane parts involves highly complex, sophisticated and expensive machines, and automating their manufacturing can save money and time, and improve safety and efficiency,” commented Balaprakash.
When will this be implemented?
Scientists utilising machine learning need to develop different models that look at many different properties of the welding process, giving different answers to which is best for different properties.
DeepHyper automates the design and development of machine-learning-based predictive models, which often involve expert-driven, trial-and-error processes. The research team stresses that no model is an absolute expression of reality and, as such, scientists are not primarily trying to find the single best predictive model and the associated welding condition. Rather, they are generating hundreds of highly accurate models, combining them to assess uncertainties in the predictions, and then seeking to use these more tested predictions in the manufacturing process, which will take time to perfect.
The team’s computationally intensive work is being enabled by supercomputing resources at the Argonne Leadership Computing Facility, a DOE Office of Science user facility.
