gruenwald-nuclear

(PHOTO BY TOMAS SEREDA)

A Purdue University-affiliated startup, Blue Wave AI Labs, is using predictive analytics to operate nuclear reactors across the United States and to help them operate as safely and efficiently as possible.

WEST LAFAYETTE – One of the hot topics in artificial intelligence and machine learning is predictive analysis – knowing the future by analyzing data from the past.

A Purdue University-affiliated startup, Blue Wave AI Labs, is using predictive analytics to operate nuclear reactors across the United States and to help them operate as safely and efficiently as possible.

Tom Gruenwald, who received his PhD in physics from the Purdue College of Science, and Gina Pattermann, a serial entrepreneur, founded Blue Wave.

Last month, Blue Wave AI Labs received a $6.9 million grant from the Department of Energy to develop predictive models of reactor components that might cause unplanned outages. The Blue Wave research team, based in Purdue Research Park in West Lafayette, will use the funds to analyze billions of nuclear reactor data points.

Team members will develop machine learning models of the useful remaining life of components to allow timely and safe replacement. Additionally, the team will create a virtual sensor platform for nuclear reactor operations and maintenance that may also be applicable to the next generation of reactors.

Blue Wave believes that in the future, the virtual sensors can be extended to a variety of energy-production systems. This is especially beneficial where it is impossible to place or read mechanical sensors, such as near the core of a nuclear reactor.

“This award will allow us to use our scientific and engineering expertise and experience, along with our innovative AI and machine learning systems, to develop solutions for better predictions of potential maintenance and other issues occurring within nuclear plants,” Gruenwald said.

Gruenwald said that the Blue Wave team is among the first in the world to use actual data from nuclear reactors to successfully create AI and machine learning models to predict future evolution of reactor properties within the complete operational and dynamic environment of nuclear plant components.

The U.S. has about 98 operating commercial nuclear reactors spread among 60 nuclear power plants in 30 states. Gruenwald said it is important to be able to analyze and predict the behavior of the components in those reactors because a single day shutdown of one reactor could lead to a loss in excess of $1 million. He said shutdowns sometimes last for weeks, directly affecting the cost of electricity for the consumer.

“Our AI algorithms provide advantages for both safety and efficiency,” Gruenwald said. “We purposely located our company in West Lafayette because Purdue and the state of Indiana both provide great resources to help startups grow. You really cannot find the combination of available talent and a supportive state government anywhere else in the country.”

Other projects for Blue Wave include using AI for development of robots to maneuver jet fighters in aerial combat as well as other AI-based projects related to national security and defense operations.