Artificial selection

Argonne scientists use artificial intelligence

“It’s like programming a coffee maker.”

When it comes to making new lightweight yet strong components for new airliners, scientists treat the process like trying to brew the most delicious cup of coffee.

Using artificial intelligence (AI) and machine learning, researchers at the US Department of Energy’s (DOE) Argonne National Laboratory intelligently and automatically select the perfect settings for another type of hot brew – the friction stir welding process, a common ingredient needed to manufacture aircraft components.

In a new collaboration with GE Research, Edison Welding Institute, and GKN Aerospace, Argonne computer scientists are harnessing the power of machine learning expertise and supercomputers in the lab. By reducing the number of costly experiments and time-consuming simulations with a new machine learning approach, they can generate accurate models that provide valuable insight into the welding process in significantly less time and at a fraction of the cost.

This approach, called DeepHyper, is a scalable machine learning package developed by Argonne computational scientist Prasanna Balaprakash and her Argonne colleagues. Machine learning is a process by which a computer can train itself to find the best answers to a particular question.

“If you’re trying to brew the best cup of coffee, you can spend many hours playing around with the many settings of the best machines,” Balaprakash said. “When trying to manufacture aircraft parts, we can avoid this by using machine learning, which gives us the ability to learn from a handful of sample parameters and identify the best from a set. of a billion possible configurations.

According to Balaprakash, the machine learning algorithm uses a training dataset of various welding conditions and parameters from which the properties of aircraft parts can be determined. From this dataset, many more possible inputs are instantly analyzed and ranked to determine which yields the best possible components.

“Making aircraft parts involves very complex, sophisticated and expensive machinery, and automating their manufacturing can save money and time, and improve safety and efficiency,” Balaprakash said.

Just as someone may prefer their coffee strong and bitter, or light and mellow, scientists using machine learning must develop different models that look at many different properties of the welding process, giving different answers as to which works 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. Because, in Balaprakash’s words, “no model is an absolute reflection of the truth”, he and his colleagues are not primarily trying to find the best predictive model and associated welding condition. Instead, they generate hundreds of highly accurate models, combine them to assess uncertainties in the predictions, and then seek to use those more tested predictions in the manufacturing process.

The team’s supercomputing work is enabled by the supercomputing resources of the Argonne Leadership Computing Facility, a DOE Office of Science user facility.

The partnership between Argonne, GE Research, Edison Welding Institute and GKN Aerospace is funded by a grant from the DOE’s Advanced Manufacturing Office. The project is called Probabilistic Machine Learning for Rapid Large-Scale and High-Rate Aerostructure Manufacturing.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts cutting-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state, and municipal agencies to help them solve their specific problems, advance American scientific leadership, and prepare the nation for a better future. With employees from more than 60 nations, Argonne is led by UChicago Argonne, LLC for the U.S. Department of Energy Office of Science.

U.S. Department of Energy Office of Science is the largest supporter of basic physical science research in the United States and strives to address some of the most pressing challenges of our time. For more information, visit https://​ener​gy​.gov/​s​c​ience.

Warning: AAAS and EurekAlert! are not responsible for the accuracy of press releases posted on EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.